© 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. 8-RES-JB
    11. 4251
    Prev
    Next
    INDEX
    Explanations

    comparisons to an overall or general situation or population

    oai_token-act-pair · gpt-3.5-turbo

    references to general or overall conditions and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.84
    rosso
    -0.80
    rus
    -0.76
    NetMessage
    -0.75
    rea
    -0.74
    friends
    -0.74
    hire
    -0.74
    dain
    -0.73
    asionally
    -0.73
    acers
    -0.72
    POSITIVE LOGITS
     equation
    1.09
     atmosphere
    1.06
     populace
    1.05
     population
    1.03
     environment
    1.02
     economy
    1.01
     situation
    1.00
     ecosystem
    1.00
     picture
    0.99
     continuum
    0.98
    Activations Density 0.277%

    No Known Activations