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. 4-RES-JB
    6. 17390
    Prev
    Next
    INDEX
    Explanations

    the birthplaces and years of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of birth and locations related to individuals

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

    No Comments

    Negative Logits
    vous
    -0.95
    uliffe
    -0.82
    asive
    -0.80
    idon
    -0.75
    keep
    -0.75
    acco
    -0.75
    noxious
    -0.74
    itiveness
    -0.72
    xual
    -0.72
    ality
    -0.71
    POSITIVE LOGITS
     Plymouth
    0.84
     Vog
    0.73
     captivity
    0.70
     exile
    0.69
    BuyableInstoreAndOnline
    0.67
     Amar
    0.67
     KL
    0.67
     Lima
    0.67
     Ame
    0.67
     Jah
    0.66
    Activations Density 0.120%

    No Known Activations