© 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. 7-RES-JB
    11. 21446
    Prev
    Next
    INDEX
    Explanations

    references to creators or authors of various works

    oai_token-act-pair · gpt-3.5-turbo

    references to creators or those involved in the production of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olit
    -0.73
    olk
    -0.70
    ishops
    -0.67
    ibaba
    -0.61
    eat
    -0.61
    phia
    -0.60
    abb
    -0.60
    eneg
    -0.59
    auna
    -0.59
    UGE
    -0.58
    POSITIVE LOGITS
    creator
    0.87
    paces
    0.79
    ãĤº
    0.78
    ãĥķãĤ¡
    0.78
    SHIP
    0.77
     laureate
    0.76
    ãĤ¼
    0.72
     creator
    0.72
    emis
    0.71
    ãĤ´
    0.70
    Activations Density 0.025%

    No Known Activations