© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8909
    Prev
    Next
    INDEX
    Explanations

    contractions of the verb "to be" with emphasis

    oai_token-act-pair · gpt-3.5-turbo

    repeated first-person singular statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Difficulty
    -0.61
    andise
    -0.60
     Faces
    -0.60
     Britann
    -0.59
     Reduce
    -0.59
     Galile
    -0.58
     occurs
    -0.57
     Awakens
    -0.57
     entails
    -0.57
     Observer
    -0.56
    POSITIVE LOGITS
     gonna
    1.33
     gotta
    0.98
     guessing
    0.85
    ajor
    0.84
     sorry
    0.82
     going
    0.81
    not
    0.80
    NOT
    0.78
    ethyst
    0.77
     not
    0.76
    Activations Density 0.017%

    No Known Activations