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. 3-RES-JB
    6. 21301
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named "Sher"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Sher"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -1.29
    lihood
    -0.79
    ktop
    -0.73
     WikiLeaks
    -0.67
     Staten
    -0.67
    vernment
    -0.66
    ãĥĩãĤ£
    -0.64
     Wikileaks
    -0.64
    xual
    -0.62
    anwhile
    -0.61
    POSITIVE LOGITS
    iffs
    1.10
    rod
    0.95
    wood
    0.92
    bar
    0.89
    der
    0.88
    atures
    0.88
    bet
    0.85
    dog
    0.83
    mans
    0.81
    min
    0.80
    Activations Density 0.005%

    No Known Activations