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

    Neuronpedia

    Jacobian LensNEW
    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. 33677
    Prev
    Next
    INDEX
    Explanations

    mentions of people, pronouns referring to individuals, and possessive forms

    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
    55
    +0.14
    0.6%
    167
    +0.13
    0.5%
    559
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.14
    0.12
    430
    +0.13
    0.21
    167
    +0.12
    -0.01
    Negative Logits
    izabeth
    -0.76
    etheless
    -0.68
     Articles
    -0.65
    ACP
    -0.63
    Dialogue
    -0.63
    Services
    -0.62
    Experience
    -0.61
    change
    -0.61
     Seym
    -0.61
     Nichols
    -0.61
    POSITIVE LOGITS
    panic
    1.13
     Majesty
    1.13
    /
    0.91
    uristic
    0.90
    mos
    0.88
    ures
    0.87
    sing
    0.86
    reditary
    0.85
    eding
    0.82
    eded
    0.81
    Activations Density 14.306%

    No Known Activations