© 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. 2-RES-JB
    11. 23174
    Prev
    Next
    INDEX
    Explanations

    names of countries

    oai_token-act-pair · gpt-3.5-turbo

    country names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioned
    -0.73
    76561
    -0.72
    vec
    -0.65
    agonist
    -0.64
    rium
    -0.64
    erb
    -0.63
    person
    -0.61
    mun
    -0.61
    eu
    -0.61
    ivas
    -0.60
    POSITIVE LOGITS
     coasts
    0.75
     Turks
    0.75
     Indies
    0.74
     Oman
    0.73
    ignty
    0.72
    PN
    0.67
     reefs
    0.66
     Kazakhstan
    0.65
     Caucasus
    0.63
    itto
    0.63
    Activations Density 0.487%

    No Known Activations