© 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. 6-RES-JB
    11. 1686
    Prev
    Next
    INDEX
    Explanations

    words related to greetings and introductions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of introductory phrases or greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exerted
    -0.76
     implanted
    -0.71
    aults
    -0.70
    ebted
    -0.70
     requisite
    -0.69
     emitted
    -0.67
    okia
    -0.67
     relied
    -0.67
     effected
    -0.66
     griev
    -0.65
    POSITIVE LOGITS
    asty
    0.78
    ffee
    0.77
     Subtle
    0.76
     Welcome
    0.75
    elcome
    0.74
    Welcome
    0.70
     Begin
    0.69
     Paradise
    0.68
    yles
    0.67
    affle
    0.67
    Activations Density 0.054%

    No Known Activations