© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 6603
    Prev
    Next
    INDEX
    Explanations

    indirect relationships or connections between entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to indirect actions or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imen
    -0.88
    ger
    -0.75
    imens
    -0.70
    "},"
    -0.70
    ingham
    -0.69
    CENT
    -0.67
    kar
    -0.65
    Ir
    -0.65
     Isle
    -0.64
     Kaufman
    -0.64
    POSITIVE LOGITS
     indirectly
    1.16
     subsid
    0.85
     graz
    0.82
     adolesc
    0.80
     sensing
    0.76
    responsible
    0.75
     sidx
    0.73
     dipping
    0.72
     cooled
    0.71
     monop
    0.71
    Activations Density 0.009%

    No Known Activations