© 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. 3-RES-JB
    11. 15287
    Prev
    Next
    INDEX
    Explanations

    numbers related to monetary values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and quantities associated with financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ches
    -0.80
    ched
    -0.79
    tern
    -0.78
    glas
    -0.76
    par
    -0.73
    hunt
    -0.72
    abol
    -0.69
    ihad
    -0.66
    alyses
    -0.65
    aukee
    -0.65
    POSITIVE LOGITS
    orsi
    0.79
    s
    0.79
     ILCS
    0.77
    Percent
    0.75
     degrees
    0.72
    480
    0.72
    470
    0.71
     volts
    0.68
    iations
    0.68
     MHz
    0.68
    Activations Density 0.049%

    No Known Activations