© 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. 11467
    Prev
    Next
    INDEX
    Explanations

    verbs in conditional or speculative statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or hypothetical scenarios

    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
     praying
    -0.72
     pursuing
    -0.71
     inspecting
    -0.68
     mobile
    -0.66
     submitting
    -0.66
     wielding
    -0.66
     naming
    -0.64
     resisting
    -0.63
     watches
    -0.63
     collaborating
    -0.63
    POSITIVE LOGITS
     suffice
    1.18
     be
    1.04
     coincide
    0.99
     occur
    0.96
     prevail
    0.92
     ripple
    0.92
     resonate
    0.90
     crumble
    0.90
     entail
    0.89
     result
    0.88
    Activations Density 0.318%

    No Known Activations