© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and notable years

    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
     guiActiveUn
    -0.83
    ider
    -0.80
    ebus
    -0.78
    pard
    -0.75
    ipel
    -0.75
    ppers
    -0.75
    elled
    -0.73
    ipher
    -0.73
    essors
    -0.71
    pper
    -0.70
    POSITIVE LOGITS
    ãĥ«
    0.78
    ãĥ¼ãĥ³
    0.78
    åŃ
    0.76
    ãĤ¦ãĤ¹
    0.76
    atsu
    0.75
    à¦
    0.75
    ãĥ¼
    0.73
    æµ
    0.71
    ptive
    0.70
    é¾įåĸļ士
    0.68
    Activations Density 0.044%

    No Known Activations