© 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. 4413
    Prev
    Next
    INDEX
    Explanations

    references to individuals with expert knowledge or credentials

    oai_token-act-pair · gpt-3.5-turbo

    references to experts in various fields

    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
     [|
    -0.70
     Agric
    -0.69
     Shades
    -0.69
    AAAA
    -0.67
    FACE
    -0.66
    strip
    -0.66
    boats
    -0.64
    à¥
    -0.64
     Winged
    -0.62
    apo
    -0.61
    POSITIVE LOGITS
    sonian
    1.02
     consulted
    0.96
     opinion
    0.84
     advise
    0.84
    ulously
    0.83
    ieth
    0.83
    udic
    0.82
     diagnose
    0.80
    ise
    0.80
     interpre
    0.79
    Activations Density 0.044%

    No Known Activations