© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19896
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers or numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those that represent counts, ratings, or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.80
    rolet
    -0.80
    igham
    -0.78
    ãĥ¼ãĥĨ
    -0.73
    atown
    -0.71
    iatrics
    -0.67
     Kamp
    -0.66
    Reviewer
    -0.64
    é¾įå¥ij士
    -0.63
     Palestin
    -0.63
    POSITIVE LOGITS
    th
    1.07
    teenth
    0.97
    ½
    0.94
    teen
    0.86
    500
    0.84
    90
    0.84
     months
    0.82
    89
    0.82
    TH
    0.81
    61
    0.80
    Activations Density 0.198%

    No Known Activations