© 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. 10-RES-JB
    11. 3306
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to legislation

    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
    »Ĵ
    -0.64
    ¬¼
    -0.60
    elve
    -0.53
    ãĥīãĥ©
    -0.53
    iphate
    -0.53
    cule
    -0.51
    izen
    -0.50
    eport
    -0.50
    inate
    -0.48
    chnology
    -0.48
    POSITIVE LOGITS
     whereas
    1.28
     but
    1.19
     although
    1.17
    but
    1.09
     though
    0.99
     hence
    0.96
    although
    0.93
     which
    0.88
     however
    0.87
     BUT
    0.87
    Activations Density 0.616%

    No Known Activations