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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34713
    Prev
    Next
    INDEX
    Explanations

    terminology related to human enhancement and transhumanism

    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
    288
    +0.05
    0.5%
    271
    +0.05
    0.5%
    649
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.05
    0.05
    288
    +0.05
    0.20
    711
    +0.05
    0.04
    Negative Logits
    NEY
    -0.39
    ieri
    -0.32
    isSpecialOrderable
    -0.31
     LINE
    -0.30
     prudent
    -0.30
    Nap
    -0.30
    rero
    -0.29
     pane
    -0.28
    Adv
    -0.28
     slee
    -0.28
    POSITIVE LOGITS
    ity
    0.62
    itarian
    0.48
     primates
    0.45
    nesses
    0.44
    ities
    0.44
    ciating
    0.44
    humans
    0.42
    ization
    0.42
    ism
    0.41
    izations
    0.41
    Activations Density 7.470%

    No Known Activations