© 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. 22967
    Prev
    Next
    INDEX
    Explanations

    legal or historical terms related to rights and legislation

    oai_token-act-pair · gpt-3.5-turbo

    topics related to civil rights and social issues

    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
    lest
    -0.84
    sth
    -0.84
    mud
    -0.77
    abase
    -0.76
    inth
    -0.75
    nect
    -0.75
    hent
    -0.74
    mberg
    -0.71
    river
    -0.67
    aband
    -0.66
    POSITIVE LOGITS
     respectively
    1.18
     alike
    1.16
     versions
    0.81
     approaches
    0.79
     economies
    0.78
    depending
    0.77
     editions
    0.76
     depending
    0.76
     sectors
    0.75
     eras
    0.75
    Activations Density 0.362%

    No Known Activations