© 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. 2-RES-JB
    11. 9376
    Prev
    Next
    INDEX
    Explanations

    phrases related to introducing or commencing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing urgency or promptness, particularly related to introduction or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sighted
    -0.84
     instinct
    -0.82
    chrom
    -0.76
    morph
    -0.70
    demand
    -0.70
    gency
    -0.66
    ethical
    -0.64
    chain
    -0.64
    Bind
    -0.62
    seekers
    -0.62
    POSITIVE LOGITS
    åħī
    0.84
     ado
    0.81
    mson
    0.77
    IUM
    0.73
     bases
    0.67
    ãĤĵ
    0.67
    ãĤī
    0.67
    е
    0.66
    uper
    0.66
    çľ
    0.66
    Activations Density 0.020%

    No Known Activations