© 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. 45952
    Prev
    Next
    INDEX
    Explanations

    phrases related to identity and personal experiences

    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
    +0.33
    1.6%
    393
    +0.17
    0.8%
    608
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.14
    669
    +0.17
    0.12
    608
    +0.11
    0.19
    Negative Logits
    aire
    -0.67
    uckland
    -0.66
    iac
    -0.65
    ensical
    -0.63
    iaries
    -0.63
     nodd
    -0.61
    flower
    -0.60
    ail
    -0.60
    soever
    -0.57
    okes
    -0.57
    POSITIVE LOGITS
     sheer
    0.98
     lack
    0.65
     necessity
    0.65
     their
    0.64
     concerns
    0.64
    é¾įå¥ij士
    0.63
     fears
    0.62
     misunderstand
    0.62
     complications
    0.61
     its
    0.60
    Activations Density 10.408%

    No Known Activations