© 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. 11-RES-JB
    11. 2263
    Prev
    Next
    INDEX
    Explanations

    parts of speech or concepts related to categories, such as chromosomes, generations, results, and profits

    oai_token-act-pair · gpt-3.5-turbo

    references to biological or genetic concepts and their associations

    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
    umbn
    -0.78
    >>>
    -0.67
    otom
    -0.67
    âĿ
    -0.67
    otonin
    -0.64
    isodes
    -0.63
    imb
    -0.63
    emp
    -0.63
    ():
    -0.62
    ¤
    -0.62
    POSITIVE LOGITS
     notwithstanding
    1.84
     being
    1.58
     preferring
    1.38
     having
    1.30
    being
    1.20
     permitting
    1.16
     seeming
    1.14
     needing
    1.13
     becoming
    1.12
     included
    1.10
    Activations Density 0.402%

    No Known Activations