© 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. 7-RES-JB
    11. 19488
    Prev
    Next
    INDEX
    Explanations

    instances of the word "usual" or synonyms like "normal" or "regular"

    oai_token-act-pair · gpt-3.5-turbo

    references to everyday human experiences and common societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psey
    -0.96
    ificantly
    -0.81
    ĸļ
    -0.75
    arching
    -0.70
    ingly
    -0.69
    outheast
    -0.69
    untarily
    -0.68
    antically
    -0.66
    orously
    -0.65
    anamo
    -0.64
    POSITIVE LOGITS
     decency
    0.66
    hello
    0.66
     procedure
    0.65
     fare
    0.64
    ISA
    0.64
    taboola
    0.63
    Rh
    0.63
    Standard
    0.61
    Newsletter
    0.60
    :{
    0.60
    Activations Density 0.427%

    No Known Activations