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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23401
    Prev
    Next
    INDEX
    Explanations

    numerical values separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or dates

    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
    olson
    -0.75
     exha
    -0.66
    phal
    -0.65
     suspic
    -0.64
    tti
    -0.64
     reluct
    -0.62
    deen
    -0.61
    llular
    -0.60
    hell
    -0.60
    everal
    -0.59
    POSITIVE LOGITS
    00
    0.91
    -+
    0.77
    inen
    0.73
    raction
    0.73
    ulse
    0.71
    escription
    0.70
    arth
    0.68
    25
    0.68
    ort
    0.68
    01
    0.63
    Activations Density 0.036%

    No Known Activations