© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 2680
    Prev
    Next
    INDEX
    Explanations

    words related to problem-solving and solutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "solve" and its variations in the context of addressing problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akening
    -0.75
    ammy
    -0.74
    akin
    -0.70
    orrow
    -0.69
     lav
    -0.68
    aving
    -0.68
    ardy
    -0.67
     reve
    -0.65
    aren
    -0.65
     showers
    -0.65
    POSITIVE LOGITS
     solve
    1.28
     solving
    1.11
     solved
    0.99
     solves
    0.98
    vable
    0.91
    ĵĺ
    0.84
     Puzzles
    0.82
    Solution
    0.81
    æ©
    0.80
     solutions
    0.79
    Activations Density 0.008%

    No Known Activations