© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    words related to eradication or abolition of something, often associated with medical interventions or societal changes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to eradication and abolition of diseases or 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
    nces
    -0.82
    ppa
    -0.72
    mont
    -0.67
     Crest
    -0.67
     Lank
    -0.64
    asers
    -0.64
    PAR
    -0.64
    lees
    -0.64
    peria
    -0.64
    ascade
    -0.64
    POSITIVE LOGITS
    icating
    1.04
    ication
    0.89
    uel
    0.84
    icator
    0.81
    icated
    0.80
    icate
    0.75
    shire
    0.75
    icates
    0.73
    ican
    0.72
    ications
    0.70
    Activations Density 0.062%

    No Known Activations