© 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. 7-RES-JB
    11. 12397
    Prev
    Next
    INDEX
    Explanations

    phrases related to making suggestions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "suggest" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.71
    percent
    -0.70
    cler
    -0.70
    pes
    -0.68
    fare
    -0.67
    gart
    -0.65
    Boy
    -0.65
    wig
    -0.65
    respective
    -0.64
    estine
    -0.64
    POSITIVE LOGITS
     suggestions
    0.76
    ively
    0.76
    ibility
    0.73
    ible
    0.71
     hypot
    0.70
    ibilities
    0.66
    eele
    0.65
    ibly
    0.64
     otherwise
    0.64
    esson
    0.64
    Activations Density 0.047%

    No Known Activations