© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18987
    Prev
    Next
    INDEX
    Explanations

    verbs expressing logical deductions or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of making sense or logic

    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
    yx
    -0.71
    scl
    -0.69
    stra
    -0.69
    tar
    -0.67
     presided
    -0.65
    phrine
    -0.65
     ILCS
    -0.63
    rina
    -0.63
    anwhile
    -0.63
    thia
    -0.63
    POSITIVE LOGITS
     sense
    1.66
    hift
    1.11
     Sense
    1.04
    sense
    1.00
     perfect
    0.98
     headlines
    0.92
     me
    0.91
     mockery
    0.82
    ENSE
    0.79
     intuitive
    0.77
    Activations Density 0.074%

    No Known Activations