© 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. 0-RES-JB
    6. 16417
    Prev
    Next
    INDEX
    Explanations

    information related to various individuals named "Dunning."

    oai_token-act-pair · gpt-3.5-turbo
    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
    ives
    -0.72
    iotic
    -0.67
    PT
    -0.66
    ami
    -0.66
    asp
    -0.65
    1001
    -0.63
     fingertips
    -0.63
     mobilize
    -0.62
    Ñĭ
    -0.60
     expressive
    -0.60
    POSITIVE LOGITS
     Dun
    3.83
    Dun
    2.42
     dun
    1.58
     Dund
    1.30
     Dul
    1.22
     Duncan
    1.22
     Dw
    1.21
     Dunn
    1.20
     Dur
    1.18
    Dur
    1.17
    Activations Density 0.007%

    No Known Activations