© 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. 4-RES-JB
    11. 15355
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to making appeals or appeals being made

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing various forms of appeals or requests

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

    No Comments

    Negative Logits
    sterdam
    -0.93
    llan
    -0.76
    isk
    -0.72
    alde
    -0.69
    auga
    -0.67
    stadt
    -0.67
    hered
    -0.64
    kes
    -0.62
    holm
    -0.62
    grad
    -0.62
    POSITIVE LOGITS
     plea
    0.77
     gauge
    0.72
    ĸļ
    0.70
     refrain
    0.70
     plead
    0.69
     Revival
    0.68
     gull
    0.68
     pleas
    0.67
     reconsider
    0.67
     appease
    0.65
    Activations Density 0.125%

    No Known Activations