© 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. 4-RES-JB
    11. 4385
    Prev
    Next
    INDEX
    Explanations

    prices or pricing information

    oai_token-act-pair · gpt-3.5-turbo

    prices or pricing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igators
    -0.78
     tragedies
    -0.70
    igating
    -0.70
    igent
    -0.67
    antha
    -0.67
    ient
    -0.66
    liners
    -0.65
    geries
    -0.65
    irlf
    -0.63
     strang
    -0.63
    POSITIVE LOGITS
    999
    1.09
    UGE
    0.88
     cents
    0.88
    ãģ¦
    0.88
    CRIPTION
    0.87
    CRIP
    0.84
    âĤ¬
    0.82
    9999
    0.82
    /#
    0.82
    ×Ļ×
    0.81
    Activations Density 0.019%

    No Known Activations