© 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. 8-RES-JB
    11. 6968
    Prev
    Next
    INDEX
    Explanations

    mentions of country names

    oai_token-act-pair · gpt-3.5-turbo

    various health-related and biological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.72
    rency
    -0.69
    ãĥ¼ãĥĨ
    -0.69
     Collider
    -0.63
     Guant
    -0.63
     CPI
    -0.61
     behav
    -0.59
     neutrality
    -0.58
     Portug
    -0.57
     circulation
    -0.57
    POSITIVE LOGITS
    ovych
    0.84
    sis
    0.75
    oslav
    0.73
    opter
    0.72
    horn
    0.70
    ws
    0.66
    icz
    0.64
    nis
    0.64
    kie
    0.63
    jen
    0.63
    Activations Density 0.372%

    No Known Activations