© 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. 10073
    Prev
    Next
    INDEX
    Explanations

    references to specific literary or movie titles

    oai_token-act-pair · gpt-3.5-turbo

    titles of works, specifically those that begin with "The."

    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
    poke
    -0.75
    />
    -0.74
    âĶĢ
    -0.74
    gpu
    -0.70
    pai
    -0.69
     irrespective
    -0.69
    CVE
    -0.69
     beware
    -0.68
    GPU
    -0.67
     forbid
    -0.67
    POSITIVE LOGITS
     Greatest
    1.19
     Lost
    1.18
    odor
    1.14
     Adventures
    1.11
     Stranger
    1.10
     Walking
    1.07
     Forgotten
    1.07
     Invisible
    1.07
     Return
    1.07
     Simpsons
    1.07
    Activations Density 0.072%

    No Known Activations