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. 5751
    Prev
    Next
    INDEX
    Explanations

    numerical values such as prices, interest rates, costs, and levels

    oai_token-act-pair · gpt-3.5-turbo

    differentials and comparisons related to scale, cost, and performance metrics

    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
    andals
    -0.70
    STEM
    -0.69
    ules
    -0.66
     Tayyip
    -0.63
    ullah
    -0.62
     Malays
    -0.62
    ister
    -0.60
     Chronicles
    -0.59
    letters
    -0.59
    thia
    -0.59
    POSITIVE LOGITS
     behest
    1.17
     expense
    1.03
     disadvantage
    0.89
     discretion
    0.86
     level
    0.85
     outset
    0.85
     mercy
    0.83
     apiece
    0.82
     disposal
    0.82
     intervals
    0.82
    Activations Density 0.395%

    No Known Activations