Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34550
    Prev
    Next
    INDEX
    Explanations

    phrases related to covert activities and clandestine operations

    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%
    288
    +0.18
    0.9%
    302
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.21
    725
    +0.18
    0.08
    723
    +0.12
    0.07
    Negative Logits
    ð
    -0.80
     Pwr
    -0.79
    ordan
    -0.74
     Atkinson
    -0.73
     GOODMAN
    -0.72
    ICAN
    -0.69
    hetti
    -0.68
    akeru
    -0.67
    ona
    -0.67
    Afee
    -0.66
    POSITIVE LOGITS
     stash
    0.83
     plotting
    0.72
    ly
    0.70
     covert
    0.69
     plot
    0.69
     sneak
    0.67
    ively
    0.67
     operatives
    0.67
     ops
    0.66
    arial
    0.66
    Activations Density 9.039%

    No Known Activations