© 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. 9-RES-JB
    11. 17066
    Prev
    Next
    INDEX
    Explanations

    words related to network structures and connections

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating complex networks or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dad
    -0.76
    bowl
    -0.75
    ayson
    -0.73
    idas
    -0.71
    inch
    -0.70
    conom
    -0.69
    amount
    -0.69
     Remastered
    -0.66
    offset
    -0.65
    group
    -0.65
    POSITIVE LOGITS
     sorts
    1.16
     contacts
    0.86
     helpers
    0.86
     goodies
    0.82
     informants
    0.81
     specialists
    0.81
     collaborators
    0.81
     superheroes
    0.81
     interconnected
    0.81
     spies
    0.78
    Activations Density 0.155%

    No Known Activations