© 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. 21617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a list of different items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate additional or supplementary information

    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
    ĸļ
    -0.82
    xit
    -0.79
    iker
    -0.76
    hyde
    -0.75
    ©¶æ
    -0.74
    opus
    -0.72
     Bake
    -0.70
    ibling
    -0.69
    hend
    -0.67
    onics
    -0.67
    POSITIVE LOGITS
     things
    1.73
     factors
    1.38
     reasons
    1.29
     considerations
    1.22
     Things
    1.19
     places
    1.18
    things
    1.15
     topics
    1.13
     thing
    1.10
    worldly
    1.10
    Activations Density 0.059%

    No Known Activations