© 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. 19684
    Prev
    Next
    INDEX
    Explanations

    mentions of siblings, specifically brothers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "brother."

    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
    mberg
    -0.79
    issions
    -0.74
    pmwiki
    -0.72
    USE
    -0.70
    argon
    -0.70
    Population
    -0.69
    orney
    -0.69
    veyard
    -0.68
    ainer
    -0.67
    alling
    -0.66
    POSITIVE LOGITS
    hood
    1.36
     brothers
    0.95
     brother
    0.94
     nephew
    0.83
    brother
    0.82
     uncle
    0.78
    gee
    0.78
    pins
    0.78
    ly
    0.77
    friend
    0.76
    Activations Density 0.025%

    No Known Activations