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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 22115
    Prev
    Next
    INDEX
    Explanations

    names containing the word "Sere" or "Pere"

    oai_token-act-pair · gpt-3.5-turbo

    the names of specific locations and individuals related to a particular event or narrative

    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
    oggle
    -0.80
    endered
    -0.79
    opped
    -0.78
    otine
    -0.76
    ambers
    -0.76
    owers
    -0.75
    oulder
    -0.72
    raft
    -0.72
    arette
    -0.71
    uyomi
    -0.71
    POSITIVE LOGITS
    chal
    0.96
    nce
    0.84
    nda
    0.83
    çĭ
    0.81
    na
    0.81
    dain
    0.79
    nt
    0.78
    ment
    0.77
    ments
    0.76
    xp
    0.76
    Activations Density 0.026%

    No Known Activations