© 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. 8-RES-JB
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional associations and unions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various professional associations and unions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efully
    -0.80
    aneously
    -0.69
    eful
    -0.67
    lier
    -0.65
    river
    -0.65
     drums
    -0.64
    ulously
    -0.62
    ctors
    -0.62
    MENTS
    -0.61
    cases
    -0.60
    POSITIVE LOGITS
    hip
    1.39
    '
    1.18
    hips
    1.15
    pace
    1.13
    paces
    1.11
    hift
    1.08
    kaya
    1.07
     Guild
    1.07
    peak
    1.04
    mith
    1.02
    Activations Density 0.238%

    No Known Activations