© 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. 12098
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various fields such as science, technology, law, and surveillance

    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
    `.
    -0.71
    %.
    -0.70
    $.
    -0.66
    irlf
    -0.65
    ebus
    -0.65
    +.
    -0.64
    Lear
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.59
    ().
    -0.59
    !".
    -0.57
    POSITIVE LOGITS
     varies
    1.57
     differs
    1.33
     depends
    1.27
     reflects
    1.24
     coincides
    1.24
     derives
    1.17
     relates
    1.17
     differed
    1.16
     extends
    1.16
     tends
    1.15
    Activations Density 0.322%

    No Known Activations