© 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. 16285
    Prev
    Next
    INDEX
    Explanations

    phrases related to totals or sums

    oai_token-act-pair · gpt-3.5-turbo

    references to aggregate quantities or totals

    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
     buttons
    -0.72
    docs
    -0.70
    tics
    -0.69
     brakes
    -0.66
     newsletters
    -0.66
    amines
    -0.66
     blockers
    -0.65
     corners
    -0.65
    zos
    -0.65
     races
    -0.64
    POSITIVE LOGITS
     ranging
    0.79
     of
    0.75
     lifespan
    0.74
     whopping
    0.72
     seven
    0.72
     nine
    0.71
     six
    0.71
     thirteen
    0.70
     eight
    0.70
     five
    0.66
    Activations Density 0.072%

    No Known Activations