© 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. 13453
    Prev
    Next
    INDEX
    Explanations

    references to physical objects like sticks

    oai_token-act-pair · gpt-3.5-turbo

    references to sticks in various contexts

    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
     unfocusedRange
    -0.80
    OTO
    -0.71
    APH
    -0.71
    actionDate
    -0.71
    âĸ¬
    -0.69
    ean
    -0.67
    ordan
    -0.67
    âĸ¬âĸ¬
    -0.66
    chid
    -0.66
    ONT
    -0.65
    POSITIVE LOGITS
    holder
    1.00
    iness
    0.95
    pole
    0.91
    holders
    0.89
    tip
    0.83
     blender
    0.82
    lihood
    0.81
    handled
    0.81
     sticks
    0.81
    handle
    0.81
    Activations Density 0.022%

    No Known Activations