© 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. 40382
    Prev
    Next
    INDEX
    Explanations

    phrases related to the design and implementation of policies and programs

    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
    481
    +0.13
    0.8%
    314
    +0.11
    0.7%
    690
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.33
    575
    +0.11
    0.20
    481
    +0.08
    0.26
    Negative Logits
     VIDEOS
    -0.50
     Andromeda
    -0.47
     Bang
    -0.47
     Everywhere
    -0.47
     Ducks
    -0.46
     Mushroom
    -0.45
     Guys
    -0.45
     cropped
    -0.45
     Forever
    -0.45
     Kore
    -0.45
    POSITIVE LOGITS
    nels
    0.67
    anus
    0.64
    istries
    0.63
    aton
    0.60
    ctor
    0.59
    rious
    0.59
    iar
    0.57
    arist
    0.56
    arily
    0.56
    xes
    0.56
    Activations Density 11.012%

    No Known Activations