© 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. 10-RES-JB
    11. 6703
    Prev
    Next
    INDEX
    Explanations

    capitalized words that may indicate titles, such as names or organizations

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to law, crime, and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lde
    -0.72
    sharp
    -0.69
    ttes
    -0.67
    ide
    -0.67
    lahoma
    -0.66
    orthern
    -0.66
    ista
    -0.66
    ria
    -0.64
    bc
    -0.64
    omics
    -0.64
    POSITIVE LOGITS
    ING
    1.77
    ER
    1.71
    EST
    1.66
    NING
    1.66
    LIN
    1.65
    LEY
    1.65
    NER
    1.64
    IENT
    1.62
    ERY
    1.62
    ET
    1.59
    Activations Density 0.210%

    No Known Activations