© 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. 10-RES-JB
    11. 11101
    Prev
    Next
    INDEX
    Explanations

    objects or parts related to mechanical devices

    oai_token-act-pair · gpt-3.5-turbo

    nouns that refer to objects and components, particularly those that serve a functional purpose

    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
    DragonMagazine
    -0.83
    Ô
    -0.80
    edIn
    -0.73
    olitics
    -0.71
    invoke
    -0.70
    é»Ĵ
    -0.69
     è£ıè¦ļéĨĴ
    -0.69
     Gamble
    -0.67
    acerb
    -0.67
    REDACTED
    -0.67
    POSITIVE LOGITS
     itself
    1.29
     shaft
    1.14
     casing
    1.14
     cavity
    1.11
     surface
    1.09
     envelope
    1.09
     enclosure
    1.06
     coil
    1.04
     spine
    1.03
     axle
    1.03
    Activations Density 0.252%

    No Known Activations