© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13205
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or ethical wrongdoing and investigations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.17
    0.9%
    576
    +0.10
    0.5%
    181
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.10
    540
    +0.10
    0.07
    126
    +0.09
    0.05
    Negative Logits
     snipp
    -0.60
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.59
     Idea
    -0.55
    IPS
    -0.54
     Fight
    -0.54
     healthier
    -0.52
    slice
    -0.52
    iku
    -0.52
     gent
    -0.51
     closures
    -0.51
    POSITIVE LOGITS
    ulence
    0.87
    onduct
    0.78
    ionage
    0.76
     perpetrated
    0.76
     involving
    0.68
    mson
    0.67
    orously
    0.66
    oided
    0.65
     manslaughter
    0.64
    rial
    0.63
    Activations Density 0.897%

    No Known Activations