© 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. 8-RES-JB
    11. 20160
    Prev
    Next
    INDEX
    Explanations

    ingredients or cooking instructions referring to making pastries, especially patties

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "att" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lda
    -0.67
     Uzbek
    -0.64
     fentanyl
    -0.61
     SIL
    -0.60
     Galile
    -0.60
     methyl
    -0.59
    Ö¼
    -0.59
    vous
    -0.58
    lect
    -0.58
     Britann
    -0.58
    POSITIVE LOGITS
    anooga
    1.46
    ributes
    1.22
    leground
    1.19
    ributed
    1.17
    itude
    1.17
    orney
    1.16
    erers
    1.11
    erer
    1.07
    itudes
    1.04
    achment
    1.03
    Activations Density 0.025%

    No Known Activations