© 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. 453
    Prev
    Next
    INDEX
    Explanations

    important keywords related to data analysis and tracking services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structure and administrative functions

    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
    inventoryQuantity
    -0.74
    ãģĦ
    -0.72
    panic
    -0.72
     unpop
    -0.71
    uders
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    çİĭ
    -0.69
    sbm
    -0.68
    picture
    -0.67
    ãĤ¨ãĥ«
    -0.67
    POSITIVE LOGITS
    ror
    0.68
     extraord
    0.64
    eker
    0.62
     specializing
    0.61
     Regulations
    0.60
     (&
    0.59
    apter
    0.59
    orde
    0.58
    orer
    0.58
    ums
    0.57
    Activations Density 0.526%

    No Known Activations