© 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. 6-RES-JB
    11. 1676
    Prev
    Next
    INDEX
    Explanations

    mentions of the number of languages a person knows

    oai_token-act-pair · gpt-3.5-turbo

    references to languages and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kus
    -0.87
    roxy
    -0.86
    ecake
    -0.84
    ilts
    -0.82
    apego
    -0.82
    oppable
    -0.81
    roleum
    -0.81
    arranted
    -0.78
    ilon
    -0.78
    rodu
    -0.78
    POSITIVE LOGITS
     spoken
    1.07
     learners
    0.98
    language
    0.95
     proficiency
    0.94
    ĨĴ
    0.94
     flu
    0.93
     interpreter
    0.90
     languages
    0.89
     translation
    0.87
     Languages
    0.84
    Activations Density 0.035%

    No Known Activations