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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14833
    Prev
    Next
    INDEX
    Explanations

    technical terms related to work processes and locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to lists and inventories

    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
     ÂŃ
    -1.69
    âĢ
    -1.41
    ÂŃ
    -1.35
     âĢķ
    -1.28
    âĢij
    -1.23
    —
    -1.20
    Åį
    -1.19
    â
    -1.11
    ï
    -1.10
    âĢİ
    -1.08
    POSITIVE LOGITS
     alot
    1.38
     doesnt
    1.29
     didnt
    1.19
     dont
    1.18
     negro
    1.16
     thru
    1.12
     americ
    1.03
     english
    1.03
     retarded
    1.02
     whats
    1.02
    Activations Density 1.221%

    No Known Activations