© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    various keywords related to technology, news, and social media

    oai_token-act-pair · gpt-3.5-turbo
    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
    chers
    -0.85
    zzle
    -0.83
    doms
    -0.81
    ches
    -0.80
    cles
    -0.80
    ged
    -0.79
    ments
    -0.78
    tons
    -0.78
    ations
    -0.77
    iform
    -0.76
    POSITIVE LOGITS
    ISH
    1.42
    OUT
    1.30
    IN
    1.30
    ASH
    1.27
    OW
    1.27
    OCK
    1.27
    IST
    1.25
    OIL
    1.25
    ACK
    1.25
    OVER
    1.24
    Activations Density 0.050%

    No Known Activations