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. 8-RES-JB
    6. 19116
    Prev
    Next
    INDEX
    Explanations

    technical and logistical challenges or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to difficulties and problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§«
    -0.82
    morning
    -0.82
    aunder
    -0.79
    hens
    -0.77
    venge
    -0.75
    tip
    -0.74
    lez
    -0.73
    orative
    -0.73
    Happy
    -0.72
    joice
    -0.72
    POSITIVE LOGITS
     inexper
    0.93
     unforeseen
    0.92
     cumbers
    0.86
     pesky
    0.84
     Firstly
    0.82
     fragmentation
    0.80
     Unable
    0.79
     inability
    0.79
     lack
    0.76
     inexperienced
    0.76
    Activations Density 0.396%

    No Known Activations