© 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. 1-RES-JB
    11. 16348
    Prev
    Next
    INDEX
    Explanations

    introductory phrases indicating the beginning of an article or story

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "This" indicating a focus on subjectivity or personal perspective in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adle
    -0.75
    pots
    -0.67
    masters
    -0.63
    aments
    -0.62
    ãĤ¹ãĥĪ
    -0.61
     Flores
    -0.60
    ãĥĺ
    -0.59
    aws
    -0.58
    tones
    -0.58
    pless
    -0.58
    POSITIVE LOGITS
    information
    0.78
     Week
    0.74
     week
    0.73
     arrang
    0.73
     Month
    0.72
     trope
    0.71
    jri
    0.71
    Adds
    0.70
     latest
    0.70
    Information
    0.70
    Activations Density 0.071%

    No Known Activations