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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13193
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate dependence or reliance on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating dependence, differentiation, or lack of something

    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
     start
    -0.74
     release
    -0.68
     catch
    -0.63
     debut
    -0.63
     fill
    -0.63
     drop
    -0.61
     go
    -0.61
     rescue
    -0.60
     pop
    -0.60
     launch
    -0.60
    POSITIVE LOGITS
     depended
    2.43
     lacked
    2.16
     differed
    2.11
     resembled
    2.11
     smelled
    2.02
     mattered
    2.01
     relied
    1.99
     consisted
    1.93
     lasted
    1.93
     belonged
    1.89
    Activations Density 0.060%

    No Known Activations