© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or potentiality

    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
    lished
    -0.66
    RESULTS
    -0.66
     elig
    -0.61
    âĹ¼
    -0.60
    76561
    -0.59
    é¾į
    -0.58
     accordingly
    -0.57
    sequently
    -0.57
    their
    -0.57
     attest
    -0.56
    POSITIVE LOGITS
     neither
    0.83
    only
    0.76
     anything
    0.74
     merely
    0.72
    nothing
    0.72
     nothing
    0.71
     only
    0.70
     Neither
    0.68
     None
    0.67
    anything
    0.66
    Activations Density 0.597%

    No Known Activations