© 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. 11-RES-JB
    11. 24068
    Prev
    Next
    INDEX
    Explanations

    proper nouns, such as movie titles or names of people

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks that indicate movie titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moder
    -0.88
     disproportionately
    -0.85
     retention
    -0.84
     hypot
    -0.84
     ranged
    -0.84
     perme
    -0.82
     disproportion
    -0.82
     escalated
    -0.82
     doctr
    -0.80
     complement
    -0.80
    POSITIVE LOGITS
    Lost
    1.69
    Untitled
    1.65
    Inside
    1.65
    Night
    1.65
    Morning
    1.64
    Breaking
    1.63
    Amazing
    1.62
    Operation
    1.62
    Living
    1.61
    Blood
    1.60
    Activations Density 0.097%

    No Known Activations