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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 22587
    Prev
    Next
    INDEX
    Explanations

    mentions of the next generation of technology or products

    oai_token-act-pair · gpt-3.5-turbo

    references to different generations of technology

    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
    orial
    -0.68
     Osw
    -0.68
    mercial
    -0.67
     frequ
    -0.64
    des
    -0.62
    esses
    -0.62
    omo
    -0.61
    ãĥ£
    -0.60
     proport
    -0.60
    enhagen
    -0.60
    POSITIVE LOGITS
     iteration
    0.85
    bps
    0.79
     installment
    0.70
     versions
    0.70
     onwards
    0.69
     version
    0.68
    idable
    0.68
     ESV
    0.67
     edition
    0.67
     batch
    0.67
    Activations Density 0.051%

    No Known Activations