© 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. 0-RES-JB
    11. 22716
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Wool"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "wool" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dar
    -0.74
    ichi
    -0.73
     APPLIC
    -0.72
    advant
    -0.72
     CM
    -0.72
     Kasich
    -0.67
    amic
    -0.67
     hitter
    -0.67
    mi
    -0.66
     mi
    -0.66
    POSITIVE LOGITS
     Wool
    4.09
     wool
    2.04
     Loft
    1.35
     feathers
    1.26
    OOL
    1.22
     Fo
    1.16
    robe
    1.08
     Dull
    1.07
     Feather
    1.06
     gown
    1.03
    Activations Density 0.040%

    No Known Activations