© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 11798
    Prev
    Next
    INDEX
    Explanations

    mentions of a large quantity or multitude of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate large quantities or counts of individuals or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     majesty
    -0.81
    ļéĨĴ
    -0.64
     omnip
    -0.63
     Brief
    -0.63
     deepest
    -0.62
    rament
    -0.61
     emptiness
    -0.60
     adequ
    -0.60
     streng
    -0.60
     ledger
    -0.60
    POSITIVE LOGITS
     of
    0.93
     (>
    0.87
    UID
    0.82
     (<
    0.71
     (~
    0.70
    aux
    0.68
     thereof
    0.64
    users
    0.64
    bang
    0.64
    metry
    0.63
    Activations Density 0.095%

    No Known Activations