© 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. 859
    Prev
    Next
    INDEX
    Explanations

    the syllable "oh"

    oai_token-act-pair · gpt-4-turbo

    the word "oh" at varying intensities, possibly indicating surprise or realization

    oai_token-act-pair · gpt-3.5-turbo

    the expression of surprise or exclamation

    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
     Legions
    -0.72
     balloons
    -0.70
    ãĥ¯
    -0.67
    */(
    -0.66
     Proced
    -0.66
     Converted
    -0.65
     Hurricanes
    -0.64
     Panther
    -0.64
     Fired
    -0.64
    è¦ļéĨĴ
    -0.63
    POSITIVE LOGITS
    oh
    1.14
    oho
    1.01
    ansen
    1.00
    oming
    1.00
    awk
    1.00
    undred
    0.99
    achi
    0.96
    oe
    0.94
    oy
    0.94
    onda
    0.94
    Activations Density 0.007%

    No Known Activations