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. 6836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternative choices or options

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or statements

    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
    ires
    -0.72
    ursday
    -0.70
    onday
    -0.67
    uesday
    -0.67
    emi
    -0.66
    IDENT
    -0.64
    orter
    -0.64
    ETS
    -0.64
    estro
    -0.64
    erest
    -0.63
    POSITIVE LOGITS
    chard
    1.21
     alternatively
    1.09
    acle
    1.06
     whatever
    1.05
    nam
    1.04
    chid
    0.98
    nery
    0.98
    ifice
    0.97
    acles
    0.96
     otherwise
    0.95
    Activations Density 0.093%

    No Known Activations