Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14880
    Prev
    Next
    INDEX
    Explanations

    names of various figures, including biblical and modern names

    oai_token-act-pair · gpt-3.5-turbo

    references to the biblical figure Moses and related concepts

    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
    straight
    -0.68
    enfranch
    -0.66
    draft
    -0.66
    amins
    -0.66
    namese
    -0.66
    fare
    -0.66
    alien
    -0.66
    chnology
    -0.65
    rive
    -0.65
     Citizen
    -0.64
    POSITIVE LOGITS
     Moses
    1.05
    theless
    0.80
    kins
    0.79
    avior
    0.78
    chool
    0.76
     Flores
    0.74
    terday
    0.70
    angelo
    0.69
    itic
    0.69
     Rebirth
    0.68
    Activations Density 0.012%

    No Known Activations