© 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. 22779
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements or scales

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant negative evaluations or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    natureconservancy
    -0.77
     behavi
    -0.77
     antioxid
    -0.73
     adolesc
    -0.72
     exha
    -0.71
     reluct
    -0.70
    EStream
    -0.68
    ĵĺ
    -0.66
    WithNo
    -0.64
    lehem
    -0.64
    POSITIVE LOGITS
    -
    2.17
    âĢij
    1.46
    -,
    1.31
    âĢIJ
    1.31
    -'
    1.21
    -[
    1.20
    "-
    1.15
    '-
    1.13
    -)
    1.06
    -"
    1.05
    Activations Density 0.523%

    No Known Activations