© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6889
    Prev
    Next
    INDEX
    Explanations

    mentions of ways to access additional content or information related to the document

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "you can" along with variations of its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arthed
    -0.75
    existent
    -0.73
    inventoryQuantity
    -0.64
    pires
    -0.61
     Matters
    -0.60
    hesive
    -0.59
    atered
    -0.58
    interstitial
    -0.58
     overpowered
    -0.57
    âĸĪâĸĪâĸĪâĸĪ
    -0.56
    POSITIVE LOGITS
     download
    1.31
    't
    1.29
     find
    1.16
     subscribe
    1.12
     browse
    1.09
     learn
    1.07
     see
    1.03
     read
    1.02
     view
    1.02
     Download
    0.98
    Activations Density 0.060%

    No Known Activations