© 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. 11-RES-JB
    11. 22434
    Prev
    Next
    INDEX
    Explanations

    negative or questioning statements about the system in use

    oai_token-act-pair · gpt-3.5-turbo

    discussions about perceptions or descriptions of reality and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unparalleled
    -0.60
     culminating
    -0.59
    accompan
    -0.57
     assorted
    -0.57
    éĩ
    -0.55
    rather
    -0.55
     progressively
    -0.54
     tantal
    -0.52
     seemingly
    -0.52
    almost
    -0.52
    POSITIVE LOGITS
     anymore
    1.65
     nor
    1.45
    yet
    1.24
    nor
    1.11
     yet
    0.97
     :(
    0.97
     slightest
    0.87
     necessarily
    0.87
     unless
    0.83
     anything
    0.82
    Activations Density 0.521%

    No Known Activations