© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23322
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate something happens in a common or expected manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common or standard occurrences

    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
    nut
    -0.67
     Cancer
    -0.67
    planes
    -0.66
    him
    -0.66
    agate
    -0.65
    ters
    -0.65
    ÄŁ
    -0.64
    Eva
    -0.64
     Ole
    -0.64
    nuts
    -0.64
    POSITIVE LOGITS
    entimes
    1.03
     exha
    0.80
     cumbers
    0.79
    pmwiki
    0.79
     encountered
    0.79
     suited
    0.77
     compr
    0.76
    ©¶æ
    0.76
     proport
    0.76
    »Ĵ
    0.74
    Activations Density 0.009%

    No Known Activations