© 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. 7-RES-JB
    11. 19470
    Prev
    Next
    INDEX
    Explanations

    languages mentioned within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to languages, particularly Spanish and Arabic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.90
    ertodd
    -0.81
    inson
    -0.80
    ividual
    -0.80
    rons
    -0.78
    olicy
    -0.77
    arf
    -0.77
    hardt
    -0.76
    vre
    -0.75
    llan
    -0.75
    POSITIVE LOGITS
     translation
    1.28
     language
    1.14
     subtitles
    1.09
     pronunciation
    1.08
     languages
    1.07
     translations
    1.04
     translator
    1.03
     Language
    1.01
     diction
    1.01
     interpreter
    0.98
    Activations Density 0.124%

    No Known Activations