© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10181
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the format of parenthesis with a number inside

    oai_token-act-pair · gpt-3.5-turbo

    list items or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advertis
    -0.68
     grocer
    -0.65
    agall
    -0.65
     rigging
    -0.62
    nam
    -0.62
    rentices
    -0.61
    buck
    -0.60
     grooming
    -0.59
     bos
    -0.59
    jug
    -0.59
    POSITIVE LOGITS
     [+
    0.99
    NK
    0.68
    eous
    0.67
    Pg
    0.64
    º
    0.64
    ãĤ´ãĥ³
    0.63
    ????
    0.63
     Whilst
    0.63
     Prot
    0.62
    %:
    0.62
    Activations Density 0.023%

    No Known Activations