© 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. 11-RES-JB
    6. 16589
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Forward"

    oai_token-act-pair · gpt-3.5-turbo

    the term "forward" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berra
    -0.72
    hod
    -0.71
    abase
    -0.71
    reon
    -0.70
    tub
    -0.69
    ========
    -0.69
    ============
    -0.68
    aters
    -0.67
    hett
    -0.66
    ======
    -0.66
    POSITIVE LOGITS
    Ħ¢
    0.85
    thinking
    0.82
     thinkers
    0.80
    dating
    0.78
     thinker
    0.77
    Iterator
    0.73
     thinking
    0.73
    ivity
    0.72
    imus
    0.70
    ive
    0.70
    Activations Density 0.056%

    No Known Activations