© 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. 1224
    Prev
    Next
    INDEX
    Explanations

    words related to substitutions or submarines

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Sub" and related variations in different 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
    isSpecialOrderable
    -0.78
    jen
    -0.70
    leck
    -0.69
    etts
    -0.66
    onies
    -0.66
    elling
    -0.65
    ocratic
    -0.65
    antine
    -0.64
    othe
    -0.63
    assetsadobe
    -0.63
    POSITIVE LOGITS
     Sub
    3.57
    Sub
    2.57
    sub
    2.16
     SUB
    2.00
     sub
    1.94
     subs
    1.81
     subp
    1.41
     Sup
    1.27
     Submission
    1.21
     Subst
    1.15
    Activations Density 0.006%

    No Known Activations