© 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. 6-RES-JB
    11. 7599
    Prev
    Next
    INDEX
    Explanations

    proper nouns, potentially related to names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, specifically related to people and places

    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
    ilic
    -0.58
     systems
    -0.52
     ropes
    -0.51
     packs
    -0.47
     ener
    -0.46
     circuitry
    -0.45
     improv
    -0.45
     bir
    -0.45
     shar
    -0.45
     wi
    -0.44
    POSITIVE LOGITS
    ighed
    0.73
    iev
    0.57
    lihood
    0.57
    uates
    0.56
    bare
    0.55
    vine
    0.55
    oeuv
    0.55
    VEN
    0.54
    IAS
    0.54
    ROR
    0.52
    Activations Density 0.511%

    No Known Activations