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. 1-RES-JB
    6. 3910
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "ahan", particularly with high activation values of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "McMahan" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    placed
    -0.69
     brightest
    -0.66
    unct
    -0.66
    AFTA
    -0.65
    unders
    -0.64
    pires
    -0.64
     webs
    -0.64
    endant
    -0.64
    Reviewed
    -0.64
     fateful
    -0.63
    POSITIVE LOGITS
    igans
    1.40
    ahan
    1.38
    igan
    1.19
    agher
    0.90
    ufact
    0.83
    stadt
    0.81
    ostic
    0.80
    uin
    0.79
    stown
    0.78
    abilia
    0.77
    Activations Density 0.003%

    No Known Activations