© 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. 8-RES-JB
    6. 6448
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating a relationship or connection between entities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and certain conjunctions indicating relationships or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.71
    Written
    -0.69
    idav
    -0.68
    >>>>>>>>
    -0.68
     Edited
    -0.64
    ascript
    -0.63
    nikov
    -0.63
    pmwiki
    -0.62
     STATES
    -0.62
     Publications
    -0.62
    POSITIVE LOGITS
    hem
    0.69
    irlf
    0.65
    days
    0.63
    selves
    0.62
    ilk
    0.61
    GF
    0.61
    ngth
    0.60
    hest
    0.59
     stride
    0.58
     predecessors
    0.58
    Activations Density 0.357%

    No Known Activations