Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2826
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.88
    auts
    -0.76
    uctor
    -0.70
    adr
    -0.67
    olver
    -0.66
    onal
    -0.65
    iton
    -0.64
    unct
    -0.64
    anche
    -0.64
    onis
    -0.63
    POSITIVE LOGITS
     periphery
    0.93
     doorstep
    0.93
     occasions
    0.91
     shelf
    0.83
     basis
    0.80
     pedest
    0.79
     eve
    0.77
     alone
    0.76
     behalf
    0.74
     occasion
    0.71
    Activations Density 0.355%

    No Known Activations