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. 6-RES-JB
    6. 7893
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names with the surname "Moy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent individuals, particularly those associated with business or public speaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.76
    ettel
    -0.65
    FTWARE
    -0.65
     geometry
    -0.64
    ãĤ·ãĥ£
    -0.63
    imilation
    -0.62
    FUL
    -0.61
    phrine
    -0.60
     seam
    -0.60
    ļéĨĴ
    -0.58
    POSITIVE LOGITS
    nih
    1.35
    owitz
    0.94
    rats
    0.90
     Moy
    0.88
    sta
    0.88
    atories
    0.85
    er
    0.80
    lan
    0.80
    sters
    0.79
    lio
    0.79
    Activations Density 0.023%

    No Known Activations