© 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. 16429
    Prev
    Next
    INDEX
    Explanations

    phrases related to considerations or aspects of a specific topic

    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
    orr
    -0.65
    stall
    -0.64
     crawl
    -0.62
    CHA
    -0.60
     cascade
    -0.59
     tangled
    -0.59
    tick
    -0.59
     cycle
    -0.59
    right
    -0.57
    gain
    -0.56
    POSITIVE LOGITS
     regards
    4.36
     regard
    2.38
     respects
    1.86
     respect
    1.45
     relation
    1.15
     terms
    1.14
    Regarding
    1.12
     hopes
    1.07
     apologies
    0.99
     endeavors
    0.98
    Activations Density 0.005%

    No Known Activations