© 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. 18615
    Prev
    Next
    INDEX
    Explanations

    specific locations or landmarks mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations or notable places

    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
    acters
    -0.74
     censored
    -0.72
     voc
    -0.71
     hyster
    -0.70
     predictably
    -0.69
     cele
    -0.69
     acron
    -0.69
     plagiar
    -0.68
     epis
    -0.68
     blacklist
    -0.68
    POSITIVE LOGITS
     Creek
    1.55
    brook
    1.31
     Meadow
    1.29
     Cove
    1.26
    haven
    1.23
     Springs
    1.22
     Point
    1.22
     Shoals
    1.21
    town
    1.20
     Ridge
    1.19
    Activations Density 0.285%

    No Known Activations