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. 18886
    Prev
    Next
    INDEX
    Explanations

    examples of sentences that start with "There is" followed by a positive or negative sentiment

    oai_token-act-pair · gpt-3.5-turbo

    statements that contain strong assertions or claims about a subject

    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
     retrie
    -0.72
    Finish
    -0.69
    eals
    -0.68
    aired
    -0.66
     Assist
    -0.64
    eal
    -0.62
     Tours
    -0.62
    agos
    -0.61
    itaire
    -0.61
    ooters
    -0.61
    POSITIVE LOGITS
     ample
    1.23
     precedent
    1.18
     anecdotal
    1.12
     evidence
    1.11
     disagreement
    1.11
     speculation
    1.11
     plenty
    1.10
    evidence
    1.07
     considerable
    1.06
     mounting
    1.04
    Activations Density 0.109%

    No Known Activations