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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10264
    Prev
    Next
    INDEX
    Explanations

    phrases related to digging or burrowing

    oai_token-act-pair · gpt-3.5-turbo

    words related to burrowing or underground activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aunder
    -0.75
    dfx
    -0.72
     Gleaming
    -0.66
    é¾įå
    -0.65
    selves
    -0.65
    uncture
    -0.64
     CLSID
    -0.63
    heet
    -0.63
     Logged
    -0.63
     Integrity
    -0.61
    POSITIVE LOGITS
    rito
    1.26
    querque
    1.25
    rowing
    1.13
    rows
    1.10
    geoning
    1.05
    ger
    1.03
    geon
    1.02
    riers
    0.98
    geons
    0.95
    row
    0.93
    Activations Density 0.014%

    No Known Activations