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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 23139
    Prev
    Next
    INDEX
    Explanations

    mentions of young boys or boys in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of boys, particularly in distressing or dangerous situations

    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
    aeda
    -0.77
     Associates
    -0.74
     Locations
    -0.67
     Places
    -0.67
     workplaces
    -0.67
    ModLoader
    -0.66
    ENCE
    -0.64
    indal
    -0.64
    location
    -0.63
     Decoder
    -0.63
    POSITIVE LOGITS
    ishly
    1.01
    hood
    0.89
    children
    0.87
     leukemia
    0.86
     boy
    0.86
    friend
    0.83
     girl
    0.80
     whom
    0.78
    ish
    0.77
    crow
    0.77
    Activations Density 0.074%

    No Known Activations