© 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. 0-RES-JB
    11. 1342
    Prev
    Next
    INDEX
    Explanations

    references to "on-demand" services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to demand and supply in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shell
    -0.69
     skull
    -0.68
     coll
    -0.66
     coloured
    -0.64
     shells
    -0.64
     ball
    -0.63
     kn
    -0.63
     dead
    -0.63
     guilty
    -0.63
     Kitt
    -0.62
    POSITIVE LOGITS
    demand
    4.18
    Demand
    3.09
     Demand
    2.64
     demand
    1.43
    LEASE
    1.27
    campus
    1.03
    condition
    1.01
    pressure
    1.00
    lease
    0.99
    need
    0.98
    Activations Density 0.022%

    No Known Activations