© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    references to specific people and places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific organizations or entities

    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
     UL
    -0.93
     Bucs
    -0.85
     Tul
    -0.82
     Tulsa
    -0.76
     Trinidad
    -0.75
    atri
    -0.75
    adoes
    -0.73
    Tab
    -0.73
     tuber
    -0.73
     Jacksonville
    -0.72
    POSITIVE LOGITS
     Me
    2.05
    Me
    1.79
     ME
    1.72
    ME
    1.56
    me
    1.53
     Meh
    1.40
     Meow
    1.32
     Megan
    1.26
     Mek
    1.13
     Mei
    1.04
    Activations Density 0.175%

    No Known Activations