© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10894
    Prev
    Next
    INDEX
    Explanations

    conditional statements referring to future actions or potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hypothetical statements or opinions

    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
     renewal
    -0.71
     Resurrection
    -0.69
     Waterloo
    -0.64
     Advertisement
    -0.63
     Bridges
    -0.60
     Sources
    -0.60
     modernization
    -0.60
     srfAttach
    -0.60
     widening
    -0.59
     unlocks
    -0.58
    POSITIVE LOGITS
     recognize
    1.07
     argue
    1.06
     perceive
    1.06
     appreciate
    1.05
     attest
    0.99
     flock
    0.99
     be
    0.99
     complain
    0.98
     understandably
    0.98
     gladly
    0.97
    Activations Density 0.175%

    No Known Activations