© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    words related to promoting or supporting something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to support and promotion

    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
     Alexandria
    -0.69
     Wol
    -0.66
     Mend
    -0.64
     Sph
    -0.63
     Supervisor
    -0.62
     mammoth
    -0.61
     Cot
    -0.61
     Poc
    -0.61
     Watkins
    -0.61
     BMC
    -0.60
    POSITIVE LOGITS
    terday
    1.17
    ardless
    1.10
    acters
    1.05
    tenance
    1.04
    actly
    1.03
    ificantly
    1.02
    etheless
    1.00
    ruction
    0.98
    antic
    0.98
    initely
    0.98
    Activations Density 0.178%

    No Known Activations