© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    sentences that start with a conjunction and end with a punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sharp or cutting objects and their implications

    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
    angel
    -0.78
    encia
    -0.69
    onds
    -0.68
    ãĤ¶
    -0.66
     Previously
    -0.64
    Boot
    -0.60
     earlier
    -0.60
    igslist
    -0.60
    ĵ
    -0.60
    Medical
    -0.58
    POSITIVE LOGITS
     whichever
    0.98
    theless
    0.84
     ALWAYS
    0.80
    depending
    0.77
     whatsoever
    0.76
     abiding
    0.74
     whatever
    0.73
     always
    0.71
     invariably
    0.70
    whatever
    0.70
    Activations Density 0.392%

    No Known Activations