© 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 Local
    9. 6-RES_SCL-AJT
    11. 32716
    Prev
    Next
    INDEX
    Explanations

    phrases describing a presentation or proposal being made to an audience

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.19
    0.9%
    642
    +0.13
    0.6%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.19
    0.07
    642
    +0.13
    0.01
    313
    +0.12
    0.06
    Negative Logits
    umph
    -0.68
    leans
    -0.64
    leen
    -0.62
    ijn
    -0.61
    tery
    -0.60
     msec
    -0.59
    sei
    -0.58
    kowski
    -0.57
     churn
    -0.56
    assin
    -0.56
    POSITIVE LOGITS
     presentations
    0.83
    icts
    0.82
    eering
    0.79
    ICT
    0.78
     Present
    0.76
    ocument
    0.73
    eers
    0.72
    emonium
    0.71
    ENTS
    0.71
     slides
    0.70
    Activations Density 7.946%

    No Known Activations