© 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. 0-RES-JB
    11. 21527
    Prev
    Next
    INDEX
    Explanations

    statements about problems being solved

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving and unresolved issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uci
    -0.96
     hire
    -0.67
     stay
    -0.65
     tilt
    -0.64
     solicit
    -0.64
    udge
    -0.63
     impression
    -0.62
     take
    -0.62
    asting
    -0.61
     arm
    -0.61
    POSITIVE LOGITS
     solved
    3.68
     unsolved
    1.79
     resolved
    1.72
     solves
    1.60
     tackled
    1.58
     cured
    1.44
     answered
    1.41
     eliminated
    1.31
     fulfilled
    1.28
     mastered
    1.27
    Activations Density 0.017%

    No Known Activations