© 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. 7-RES-JB
    11. 13400
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numbers, particularly "four" and "five"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tch
    -0.78
    fw
    -0.75
    Dialogue
    -0.65
     Collider
    -0.64
     srfAttach
    -0.63
     Advertisement
    -0.62
    haps
    -0.62
    verty
    -0.61
    volt
    -0.60
    agine
    -0.60
    POSITIVE LOGITS
     sides
    0.98
     phases
    0.96
     sexes
    0.90
     facets
    0.90
    ieth
    0.88
     genders
    0.83
     halves
    0.80
     quarters
    0.79
     branches
    0.78
     corners
    0.77
    Activations Density 0.029%

    No Known Activations