© 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. 1-RES-JB
    11. 3328
    Prev
    Next
    INDEX
    Explanations

    countries, names, and medical conditions corresponding to the term "adal."

    oai_token-act-pair · gpt-3.5-turbo

    words related to geographical locations or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.79
     Cosponsors
    -0.73
    REE
    -0.72
    ðĿ
    -0.71
    CHA
    -0.71
    ALK
    -0.69
     Doct
    -0.69
    DW
    -0.68
    ACTED
    -0.67
    ILLE
    -0.67
    POSITIVE LOGITS
    adal
    1.38
    adian
    0.92
    interstitial
    0.88
    etric
    0.85
    ican
    0.85
    ilitary
    0.84
    icans
    0.83
    ayan
    0.82
    adan
    0.82
    etrical
    0.78
    Activations Density 0.005%

    No Known Activations