© 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. 16341
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Or" often appearing at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Or"

    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
    pering
    -0.78
    IDENT
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    uristic
    -0.75
    Material
    -0.72
    pered
    -0.71
    perature
    -0.69
     VIDEOS
    -0.67
    ãĤ©
    -0.65
    ãĥĺãĥ©
    -0.64
    POSITIVE LOGITS
    Else
    1.10
    chard
    1.05
    leans
    1.00
    phans
    1.00
    lando
    1.00
    thodox
    0.98
    acles
    0.97
    ifice
    0.96
    phan
    0.94
    ific
    0.94
    Activations Density 0.020%

    No Known Activations