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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17220
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and solutions

    oai_token-act-pair · gpt-3.5-turbo

    the concept of problem-solving

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

    No Comments

    Negative Logits
    ammy
    -0.70
    ardy
    -0.70
    avia
    -0.67
    treated
    -0.66
    umption
    -0.65
    head
    -0.65
    spring
    -0.65
    oths
    -0.65
    oak
    -0.64
    acid
    -0.64
    POSITIVE LOGITS
     solve
    1.04
    ĵĺ
    0.96
     solving
    0.92
    vable
    0.91
    idian
    0.80
     solves
    0.80
     Puzzles
    0.77
    itaire
    0.77
     puzzles
    0.76
     solved
    0.75
    Activations Density 0.013%

    No Known Activations