© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3770
    Prev
    Next
    INDEX
    Explanations

    phrases containing the expression "After all," before making a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that express uncertainty or conditionality

    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
    alysed
    -0.71
    SN
    -0.68
    ENC
    -0.66
    exit
    -0.64
    lem
    -0.62
    ihar
    -0.62
    RM
    -0.61
    MSN
    -0.61
    Pont
    -0.61
    pec
    -0.61
    POSITIVE LOGITS
     there
    0.83
     nobody
    0.81
     we
    0.76
     isn
    0.76
     wouldn
    0.76
     unlike
    0.76
    nob
    0.76
     suppose
    0.76
     shouldn
    0.75
     they
    0.75
    Activations Density 0.065%

    No Known Activations