© 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. 11811
    Prev
    Next
    INDEX
    Explanations

    names related to the brand "Holtz" and numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific patterns related to firearms or weaponry

    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
    Ô
    -0.63
     aggregation
    -0.61
     Atom
    -0.60
     Perspective
    -0.57
     vitro
    -0.55
    isconsin
    -0.55
     phased
    -0.55
    ermott
    -0.54
     Alz
    -0.54
     moot
    -0.54
    POSITIVE LOGITS
    rity
    0.81
    horn
    0.73
    Mine
    0.73
    andise
    0.72
    beck
    0.70
    ãĤ·ãĥ£
    0.68
    uments
    0.66
    Condition
    0.65
    ific
    0.62
    riber
    0.62
    Activations Density 0.175%

    No Known Activations