© 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. 2111
    Prev
    Next
    INDEX
    Explanations

    emoticons or keyboard symbols indicating sentiment or expression

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols, likely indicating the presence of non-standard characters or formatting

    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
    ¥ŀ
    -0.66
     Citiz
    -0.63
     Gain
    -0.61
     metic
    -0.60
     perspect
    -0.60
     snowball
    -0.59
     Gardens
    -0.59
     Folder
    -0.59
    geries
    -0.56
     Learns
    -0.55
    POSITIVE LOGITS
    âĸł
    0.82
    blank
    0.77
    cffffcc
    0.76
    =-=-
    0.75
    =~=~
    0.75
    Ïī
    0.73
     denotes
    0.73
    unknown
    0.71
    endif
    0.70
    =-=-=-=-=-=-=-=-
    0.69
    Activations Density 0.115%

    No Known Activations