Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5509
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to individuals' titles or positions, such as "dean" or "FBI"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to positions of authority or leadership, particularly "dean" and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.80
    umatic
    -0.73
     desp
    -0.73
     licence
    -0.72
     coli
    -0.70
    ð
    -0.67
     Chau
    -0.66
     è£ıç
    -0.65
     Maduro
    -0.63
    addons
    -0.63
    POSITIVE LOGITS
    olin
    2.03
     Streets
    1.53
     Gins
    1.45
     summarized
    1.41
     dean
    1.30
     summed
    1.30
     Fein
    1.18
    elin
    1.16
     Giuliani
    1.13
     Gin
    1.05
    Activations Density 0.061%

    No Known Activations