© 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. 9-RES-JB
    11. 3519
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal and existential reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heck
    -0.87
     Impact
    -0.86
    Ops
    -0.86
     Boom
    -0.83
     Plus
    -0.82
    Kids
    -0.80
    Nick
    -0.78
     Doug
    -0.78
     AJ
    -0.77
    Wow
    -0.76
    POSITIVE LOGITS
     scarcely
    1.30
     consec
    1.27
     hereafter
    1.25
     tremb
    1.20
     doubtless
    1.18
     thence
    1.14
     discern
    1.10
     vain
    1.10
    ,—
    1.08
     endeav
    1.07
    Activations Density 0.443%

    No Known Activations