© 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. 18079
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    sections containing numerical data or statistics

    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
    mbuds
    -0.69
    cheat
    -0.66
    lections
    -0.63
    hement
    -0.61
    cules
    -0.61
    ataka
    -0.60
    cius
    -0.60
     manoeuv
    -0.60
    abwe
    -0.59
     experien
    -0.58
    POSITIVE LOGITS
    ³³³
    0.67
    ³³³³³³³³
    0.66
    ³³³³
    0.65
    eways
    0.59
    Rh
    0.59
    ulty
    0.58
    VERTISEMENT
    0.57
    Forest
    0.56
    使
    0.56
     Related
    0.56
    Activations Density 0.125%

    No Known Activations