© 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. 10-RES-JB
    11. 21029
    Prev
    Next
    INDEX
    Explanations

    words related to completing tasks or actions successfully

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with achieving goals or completing tasks

    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
    Ħ¢
    -0.82
    ARB
    -0.74
    PLA
    -0.70
    ozo
    -0.70
    osate
    -0.68
    CHAT
    -0.66
     Bubble
    -0.63
    )=(
    -0.62
    WT
    -0.62
     chrom
    -0.62
    POSITIVE LOGITS
    ishing
    1.35
    ishment
    1.28
    ices
    1.22
    ishes
    1.21
    ice
    1.21
    isher
    1.03
    ished
    0.96
    ishers
    0.95
    ication
    0.94
    icating
    0.85
    Activations Density 0.067%

    No Known Activations