© 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. 4-RES-JB
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    numbers presented as quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical measures or numerical data

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

    No Comments

    Negative Logits
    inger
    -0.67
     Myr
    -0.65
    bley
    -0.60
     Rafael
    -0.60
     Alger
    -0.59
    Hor
    -0.59
     Rue
    -0.58
    Palest
    -0.57
     spat
    -0.56
    cients
    -0.55
    POSITIVE LOGITS
    hiba
    0.77
     Expend
    0.76
    Required
    0.72
    incial
    0.71
    gross
    0.70
    urden
    0.70
    isations
    0.69
     expenditures
    0.68
    owment
    0.68
    ãĥ¯ãĥ³
    0.67
    Activations Density 0.192%

    No Known Activations