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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 479
    Prev
    Next
    INDEX
    Explanations

    locations based on street intersections

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and their intersections

    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
     confir
    -0.90
    cffff
    -0.89
     therap
    -0.81
     carbohyd
    -0.78
     unden
    -0.77
     redund
    -0.74
     pse
    -0.72
     nomine
    -0.72
     equival
    -0.72
     glim
    -0.71
    POSITIVE LOGITS
     Broadway
    1.36
     Eighth
    1.34
     Seventh
    1.33
     Fifth
    1.32
     Sixth
    1.29
     Ninth
    1.28
     Eucl
    1.26
     Market
    1.24
     Fourth
    1.21
     Chest
    1.19
    Activations Density 0.080%

    No Known Activations