© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to taking action

    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
    bestos
    -0.77
    zona
    -0.73
    anmar
    -0.68
    ushima
    -0.67
    ivia
    -0.66
    plane
    -0.64
     plateau
    -0.64
    gins
    -0.63
     subt
    -0.63
    ento
    -0.62
    POSITIVE LOGITS
    Fight
    3.10
     Brave
    1.61
     Messenger
    1.44
     messenger
    1.42
     Nim
    1.34
     Commander
    1.24
    imble
    1.19
    Brave
    1.13
     provoked
    1.00
     Clash
    0.96
    Activations Density 0.051%

    No Known Activations