© 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. 4-RES-JB
    11. 10889
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "an"

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "an" in various contexts

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

    No Comments

    Negative Logits
    BLE
    -0.79
    Things
    -0.76
     pupils
    -0.73
    ï¸
    -0.71
    bots
    -0.71
     spreads
    -0.71
    cules
    -0.70
     Turns
    -0.68
    hood
    -0.68
    bane
    -0.67
    POSITIVE LOGITS
    abolic
    1.06
    esthetic
    1.04
    onym
    0.99
    omal
    0.97
    agram
    0.96
    alogue
    0.93
    onymous
    0.85
    cients
    0.85
    unciation
    0.84
    ointed
    0.83
    Activations Density 0.260%

    No Known Activations