© 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. 10-RES-JB
    11. 12274
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychological and emotional themes

    oai_token-act-pair · gpt-3.5-turbo

    elements related to character development and emotional themes in narratives

    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
    Registration
    -0.75
     obsolete
    -0.75
     expired
    -0.73
    Congratulations
    -0.71
    dat
    -0.71
    ITNESS
    -0.69
     Manufacturer
    -0.69
    Currently
    -0.68
     Registration
    -0.68
     Registered
    -0.68
    POSITIVE LOGITS
     juxtap
    1.29
     deft
    1.23
     culmin
    1.14
     subtly
    1.13
     climax
    1.09
     brilliantly
    1.08
     beautifully
    1.08
     narrator
    1.07
     unfolds
    1.07
     narr
    1.06
    Activations Density 0.681%

    No Known Activations