© 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. 13993
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood, possibility, or appearance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of the verb "be" in various contexts

    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
    aths
    -0.79
    atives
    -0.72
    arios
    -0.71
    alez
    -0.68
    ascript
    -0.66
    aft
    -0.66
    ropolis
    -0.65
    ahs
    -0.64
    arks
    -0.62
    enic
    -0.61
    POSITIVE LOGITS
     slowing
    0.75
    ono
    0.73
     stuck
    0.72
     grav
    0.71
     suppl
    0.71
     kindred
    0.70
     piling
    0.69
     circling
    0.69
     plateau
    0.67
     slipping
    0.67
    Activations Density 0.135%

    No Known Activations