© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 14491
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those related to the context of the narrative

    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
     Arabia
    -0.75
    ERAL
    -0.73
    cap
    -0.71
    gered
    -0.71
    AME
    -0.71
    ership
    -0.71
    odiac
    -0.70
    psc
    -0.70
    ebus
    -0.69
    ghai
    -0.68
    POSITIVE LOGITS
     Browne
    1.32
     millenn
    0.84
     challeng
    0.83
     Byrne
    0.78
     livest
    0.78
    anas
    0.76
     Tiff
    0.74
    itton
    0.71
    elsius
    0.71
     squats
    0.71
    Activations Density 0.005%

    No Known Activations