© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4908
    Prev
    Next
    INDEX
    Explanations

    examples or instances of something within a category or list

    oai_token-act-pair · gpt-3.5-turbo

    phrases that exemplify or provide specific examples of concepts

    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
     EVER
    -0.81
    :-
    -0.71
     EVERY
    -0.69
    cember
    -0.69
     brill
    -0.67
     2500
    -0.66
     negro
    -0.65
     tyr
    -0.65
     absolutely
    -0.64
     6000
    -0.64
    POSITIVE LOGITS
    rather
    1.11
     instead
    1.08
    instead
    1.06
     rather
    1.04
     Instead
    0.85
    âĢ
    0.81
    Instead
    0.79
     Rather
    0.78
     or
    0.77
     versus
    0.76
    Activations Density 0.966%

    No Known Activations