© 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. 23907
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "knew."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "knew" 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
    pmwiki
    -0.79
    */(
    -0.69
    anchester
    -0.69
    atre
    -0.68
    ema
    -0.68
    amic
    -0.66
    enary
    -0.65
    attery
    -0.64
    eware
    -0.64
     exting
    -0.63
    POSITIVE LOGITS
     beforehand
    1.27
     sooner
    1.01
     instinctively
    0.84
     immediately
    0.79
     exactly
    0.75
     then
    0.73
     instantly
    0.73
     there
    0.71
     nothing
    0.71
     ahead
    0.71
    Activations Density 0.112%

    No Known Activations