Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14053
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating the conclusion or end of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating endings or closures of situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vich
    -0.78
     Adin
    -0.69
    listed
    -0.65
    estate
    -0.63
    oir
    -0.63
    ilk
    -0.60
    iolet
    -0.60
    hower
    -0.59
     Licensed
    -0.59
    iar
    -0.59
    POSITIVE LOGITS
     halt
    1.27
     conclusion
    1.19
     climax
    1.08
     scree
    1.02
     abrupt
    1.02
     culmination
    0.96
     fruition
    0.93
     end
    0.92
     stop
    0.88
     realization
    0.86
    Activations Density 0.054%

    No Known Activations