Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16250
    Prev
    Next
    INDEX
    Explanations

    specific actions or requirements stated in a formal or regulatory context

    oai_token-act-pair · gpt-3.5-turbo

    language related to voting and participation

    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
    Had
    -0.77
     Had
    -0.68
    ãĥķãĤ©
    -0.67
     Were
    -0.63
    emed
    -0.60
     WATCHED
    -0.59
    had
    -0.58
    wered
    -0.58
    ãĥ´ãĤ¡
    -0.57
    sed
    -0.55
    POSITIVE LOGITS
     is
    1.43
     will
    1.39
     constitutes
    1.37
     becomes
    1.35
     occurs
    1.32
     applies
    1.31
     goes
    1.30
     qualifies
    1.30
     must
    1.30
     begins
    1.28
    Activations Density 0.921%

    No Known Activations