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. 10-RES-JB
    6. 7421
    Prev
    Next
    INDEX
    Explanations

    conditional phrases starting with "What if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or "what if" scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igmatic
    -0.90
    ngth
    -0.87
     pione
    -0.78
    abre
    -0.76
    nect
    -0.76
    dayName
    -0.74
    akable
    -0.72
    gently
    -0.70
    enfranch
    -0.69
    WAYS
    -0.69
    POSITIVE LOGITS
     someone
    1.01
     somebody
    1.00
     we
    0.96
     someday
    0.90
     there
    0.87
     you
    0.84
     they
    0.82
     everyone
    0.81
     everybody
    0.79
     Mrs
    0.75
    Activations Density 0.066%

    No Known Activations