© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9161
    Prev
    Next
    INDEX
    Explanations

    email addresses and hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting symbols used in digital text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.73
    aceae
    -0.70
    acea
    -0.66
     Marino
    -0.63
     Refuge
    -0.59
     Jury
    -0.59
    landish
    -0.59
     Advertisement
    -0.58
     Proposition
    -0.58
     Scorpion
    -0.58
    POSITIVE LOGITS
    agall
    0.84
    dit
    0.78
    oslav
    0.77
    nr
    0.73
    gz
    0.70
    zx
    0.70
    mr
    0.69
    nl
    0.69
    dl
    0.67
    kr
    0.66
    Activations Density 0.342%

    No Known Activations