© 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. 9-RES-JB
    11. 9124
    Prev
    Next
    INDEX
    Explanations

    phrases related to product specifications and configurations

    oai_token-act-pair · gpt-3.5-turbo

    terms describing shapes and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    financial
    -0.77
    ibli
    -0.73
    ipl
    -0.71
    esta
    -0.69
    arious
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    awar
    -0.66
    actionDate
    -0.65
    foreseen
    -0.64
    entin
    -0.64
    POSITIVE LOGITS
     option
    1.10
     preferred
    1.08
     favoured
    1.07
     prevailed
    1.03
     preferable
    0.94
     adopted
    0.94
     scheme
    0.89
     favored
    0.89
     prevail
    0.84
     prev
    0.83
    Activations Density 0.479%

    No Known Activations