© 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. 1-RES-JB
    11. 22870
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific entity or organization, likely related to news and events

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity represented by the abbreviation "HM."

    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
    gets
    -0.72
    margin
    -0.71
    feed
    -0.68
    Ô
    -0.68
     Janeiro
    -0.67
    lihood
    -0.65
     Marketable
    -0.65
    PsyNetMessage
    -0.64
    âķ
    -0.64
    66666666
    -0.63
    POSITIVE LOGITS
     HM
    1.17
    HM
    0.89
    DOM
    0.83
    ERG
    0.82
    IME
    0.81
    TY
    0.79
    ailability
    0.78
    itage
    0.72
    HT
    0.71
    APH
    0.71
    Activations Density 0.010%

    No Known Activations