© 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. 20220
    Prev
    Next
    INDEX
    Explanations

    descriptions of retaining certain qualities while incorporating new elements

    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
     Suppose
    -0.76
     intercepted
    -0.71
     PRESIDENT
    -0.71
     overhe
    -0.71
     worthless
    -0.70
     interceptions
    -0.68
    ulia
    -0.67
     filib
    -0.67
     papers
    -0.67
    deb
    -0.67
    POSITIVE LOGITS
     homage
    1.27
     styl
    1.07
     themes
    1.06
     minimalist
    1.05
    ampunk
    1.04
     genres
    1.04
     realism
    1.03
     genre
    1.02
     nostalgic
    1.01
     futuristic
    1.01
    Activations Density 0.583%

    No Known Activations