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. 5415
    Prev
    Next
    INDEX
    Explanations

    solutions or proposed actions to various problems or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to solutions or remedies for various problems and crises

    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
    prints
    -0.73
    rob
    -0.69
    rolled
    -0.67
    head
    -0.67
    arlane
    -0.65
    olds
    -0.65
    oths
    -0.64
    avia
    -0.64
    asts
    -0.63
    awar
    -0.62
    POSITIVE LOGITS
     solution
    0.91
     solve
    0.89
    olution
    0.86
     solutions
    0.84
     solving
    0.80
     thereto
    0.77
    Solution
    0.74
    xual
    0.74
     Solution
    0.73
    olutions
    0.72
    Activations Density 0.022%

    No Known Activations