© 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. 21714
    Prev
    Next
    INDEX
    Explanations

    phrases related to making things easier, clearer, or better in some way

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize ease, clarity, and improvement

    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
    staking
    -0.68
     remnants
    -0.63
    accompan
    -0.59
    sha
    -0.58
     inexper
    -0.56
     similarities
    -0.55
     previews
    -0.55
     Providence
    -0.54
     glitches
    -0.54
    utical
    -0.54
    POSITIVE LOGITS
    ends
    0.82
    lier
    0.75
    atable
    0.74
    ible
    0.74
     easier
    0.74
    accessible
    0.70
    able
    0.70
     attractive
    0.69
    enable
    0.69
    achable
    0.68
    Activations Density 0.179%

    No Known Activations