© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    text related to problems and solutions

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and potential solutions

    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
     oath
    -0.71
     Rhythm
    -0.66
    indal
    -0.65
     Towers
    -0.62
    âĢ¢âĢ¢
    -0.60
     Horus
    -0.60
     pound
    -0.60
     Seventh
    -0.60
     Choice
    -0.59
     Oath
    -0.59
    POSITIVE LOGITS
     solved
    1.49
     remed
    1.45
     resolved
    1.39
     addressed
    1.26
     corrected
    1.23
     dealt
    1.19
     cured
    1.16
     tackled
    1.15
     mit
    1.14
     erad
    1.12
    Activations Density 0.370%

    No Known Activations