© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 20430
    Prev
    Next
    INDEX
    Explanations

    the phrase "In any" followed by a subsequent word

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "any," indicating a focus on generality or inclusivity 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
    redients
    -0.77
    endas
    -0.77
    eps
    -0.74
    tp
    -0.67
    entin
    -0.67
    oppers
    -0.66
    IDES
    -0.65
    wings
    -0.64
    illard
    -0.63
    irds
    -0.63
    POSITIVE LOGITS
     case
    1.19
     conceivable
    1.15
     meaningful
    1.13
     event
    1.09
     circumstance
    1.08
     sane
    1.02
     sensible
    0.96
     capacity
    0.90
     reasonable
    0.90
     given
    0.89
    Activations Density 0.037%

    No Known Activations