© 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. 16809
    Prev
    Next
    INDEX
    Explanations

    the expression "all too [adjective]."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating excess or being overly frequent

    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
    instein
    -0.76
    yip
    -0.73
    igs
    -0.72
    cius
    -0.72
    yout
    -0.70
    raise
    -0.69
    ycle
    -0.68
    aea
    -0.67
    ership
    -0.67
    oust
    -0.66
    POSITIVE LOGITS
     eager
    0.66
     prevalent
    0.66
    entimes
    0.65
     evident
    0.65
     soon
    0.64
     imaginable
    0.64
     painfully
    0.64
    Much
    0.63
    ãĤ»
    0.62
     adv
    0.62
    Activations Density 0.038%

    No Known Activations