© 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. 4-RES-JB
    11. 11377
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and similar prepositions indicating location or context

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

    No Comments

    Negative Logits
     bolted
    -0.66
     PLEASE
    -0.63
     debuted
    -0.63
     %%
    -0.62
    RM
    -0.60
     flagged
    -0.59
    0000000000000000
    -0.59
     glitches
    -0.59
     pegged
    -0.59
     incumb
    -0.57
    POSITIVE LOGITS
     accordance
    1.27
    clus
    1.26
     relation
    1.23
     conjunction
    1.21
     regards
    1.13
    escap
    1.12
     order
    1.12
     lieu
    1.11
     situ
    1.11
     regard
    1.08
    Activations Density 0.678%

    No Known Activations