© 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. 10-RES-JB
    11. 1079
    Prev
    Next
    INDEX
    Explanations

    locations and arrangements of objects within a space

    oai_token-act-pair · gpt-3.5-turbo

    situational descriptions involving various locations and arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vows
    -0.68
    phony
    -0.67
     rapists
    -0.64
    fail
    -0.63
     successful
    -0.63
    failed
    -0.61
     histories
    -0.60
     revolt
    -0.59
     Failed
    -0.59
     rewritten
    -0.58
    POSITIVE LOGITS
     underneath
    1.32
     located
    1.30
     beside
    1.29
     upstairs
    1.29
     downstairs
    1.29
     somewhere
    1.27
     inside
    1.27
    inside
    1.25
     beneath
    1.24
    near
    1.21
    Activations Density 0.752%

    No Known Activations