© 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. 0-RES-JB
    11. 16430
    Prev
    Next
    INDEX
    Explanations

    phrases related to contributions or contradictions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monk
    -0.67
     Reboot
    -0.66
     Palace
    -0.65
    ilee
    -0.65
     lyn
    -0.65
     bells
    -0.64
     vows
    -0.63
     MBA
    -0.63
     undergrad
    -0.62
     knee
    -0.62
    POSITIVE LOGITS
    cont
    3.98
    Cont
    2.63
     Cont
    1.79
    CONT
    1.66
     CONT
    1.40
    dist
    1.17
    contact
    1.17
     cont
    1.16
    comp
    1.16
    controller
    1.11
    Activations Density 0.006%

    No Known Activations