Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 8745
    Prev
    Next
    INDEX
    Explanations

    the name "Ko" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the candidates in a political context, particularly focusing on "Ko" and "Everton."

    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
    AAF
    -0.71
    cled
    -0.68
    pire
    -0.67
    leader
    -0.65
    FUL
    -0.65
    ================================
    -0.65
    ============
    -0.65
     glands
    -0.64
    monary
    -0.63
    ideshow
    -0.63
    POSITIVE LOGITS
    ishly
    0.85
    ish
    0.82
    arding
    0.80
     Stam
    0.72
    oro
    0.71
     Kafka
    0.71
    bats
    0.70
    ozo
    0.70
    lins
    0.70
    ono
    0.68
    Activations Density 0.044%

    No Known Activations