© 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. 15230
    Prev
    Next
    INDEX
    Explanations

    names related to a specific title or profession (Maj)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Maj" and its variations in relation to other subjects

    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
     Gingrich
    -0.70
     damned
    -0.64
     IMAGES
    -0.63
     Hurricanes
    -0.62
    clusive
    -0.62
     Rainbow
    -0.62
    Pope
    -0.61
     drive
    -0.61
     Beckham
    -0.61
    flush
    -0.59
    POSITIVE LOGITS
    estic
    1.05
    ournal
    0.97
    ouri
    0.97
    noon
    0.92
    insk
    0.87
    arro
    0.85
    undai
    0.83
    adier
    0.83
    alla
    0.82
    iors
    0.81
    Activations Density 0.008%

    No Known Activations