© 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. 0-RES-JB
    11. 22343
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "chains" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to commercial entities or brands within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofer
    -0.68
    poll
    -0.68
    application
    -0.64
    ini
    -0.62
    irin
    -0.62
    PRO
    -0.61
    ESA
    -0.60
    othy
    -0.60
    ono
    -0.60
    enhagen
    -0.60
    POSITIVE LOGITS
     chains
    4.32
     Chains
    2.84
     chain
    2.83
    chains
    2.43
     Chain
    2.11
    chain
    2.04
    Chain
    1.93
     chained
    1.51
     ropes
    1.17
     loops
    1.17
    Activations Density 0.015%

    No Known Activations