© 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. 3989
    Prev
    Next
    INDEX
    Explanations

    general concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to general concepts or broad themes

    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
    ÄŁ
    -0.79
    bley
    -0.75
    ï¸
    -0.74
     Nikki
    -0.73
    Reb
    -0.70
     Carbuncle
    -0.70
    lda
    -0.69
    lyn
    -0.68
    Diamond
    -0.68
    rette
    -0.68
    POSITIVE LOGITS
    izations
    1.16
     relativity
    1.04
    ization
    0.98
    izable
    0.95
     overview
    0.94
    isations
    0.93
    izing
    0.92
    arily
    0.90
    ised
    0.90
    amental
    0.84
    Activations Density 0.019%

    No Known Activations