© 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. 10156
    Prev
    Next
    INDEX
    Explanations

    quantitative values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express approximate quantities or estimates

    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
    iments
    -0.76
    ters
    -0.75
    oa
    -0.73
    Reviewer
    -0.73
     Bomber
    -0.71
    ieu
    -0.70
    ysis
    -0.65
    upon
    -0.65
    tein
    -0.64
     Shame
    -0.63
    POSITIVE LOGITS
    Ĥİ
    0.93
    Ń·
    0.80
     approximate
    0.79
     analogous
    0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.76
    PsyNetMessage
    0.75
    atility
    0.72
    âĪ
    0.72
     compr
    0.72
    ptoms
    0.70
    Activations Density 0.009%

    No Known Activations