© 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. 8-RES-JB
    11. 3037
    Prev
    Next
    INDEX
    Explanations

    references to the country of Spain

    oai_token-act-pair · gpt-3.5-turbo

    references to Spain and the Spanish context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.93
    ertodd
    -0.85
    ochond
    -0.81
    oscope
    -0.80
    mble
    -0.78
    olulu
    -0.76
    ysis
    -0.74
    maxwell
    -0.73
    chens
    -0.71
    roleum
    -0.71
    POSITIVE LOGITS
     Inquisition
    1.29
     Nieto
    0.92
     Libre
    0.83
     pes
    0.82
     Rican
    0.80
     Fork
    0.79
     moss
    0.75
     jails
    0.74
     Ig
    0.70
     MX
    0.70
    Activations Density 0.028%

    No Known Activations