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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13135
    Prev
    Next
    INDEX
    Explanations

    conditional options or choices

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements about conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enormously
    -0.62
    VERTISEMENT
    -0.60
     immensely
    -0.59
     Bigfoot
    -0.59
     Havana
    -0.56
     Helsinki
    -0.55
     ammonia
    -0.54
    imar
    -0.54
     Chattanooga
    -0.53
     Pony
    -0.53
    POSITIVE LOGITS
    Else
    1.13
    acle
    0.95
    abouts
    0.94
     alternatively
    0.92
    depending
    0.87
    phans
    0.86
     equivalent
    0.79
    chard
    0.79
    acles
    0.75
    thodox
    0.75
    Activations Density 0.295%

    No Known Activations