© 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. 1211
    Prev
    Next
    INDEX
    Explanations

    phrases related to information consumption and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    references to media consumption and social perception

    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
     patience
    -0.78
     weakening
    -0.75
     precaution
    -0.73
     streng
    -0.73
     bankruptcy
    -0.73
     weakened
    -0.71
    Weak
    -0.71
     unification
    -0.68
     impossibility
    -0.67
     Prohibition
    -0.65
    POSITIVE LOGITS
    stream
    0.85
    weet
    0.85
    ritten
    0.80
    watching
    0.79
     tweeted
    0.79
     read
    0.78
    talk
    0.78
    ograph
    0.77
     aired
    0.77
    present
    0.76
    Activations Density 0.358%

    No Known Activations