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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13132
    Prev
    Next
    INDEX
    Explanations

    words related to dirtiness or decay

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gr."

    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
    phrine
    -0.85
    )=(
    -0.77
    vention
    -0.74
    hibition
    -0.69
    ership
    -0.69
    manship
    -0.66
    âĹ¼
    -0.66
    ezvous
    -0.65
    PORT
    -0.65
    idas
    -0.65
    POSITIVE LOGITS
    udge
    1.20
    umpy
    1.18
    udging
    1.16
    aciously
    1.15
    iffin
    1.07
    inder
    1.01
    iddle
    1.00
    ained
    1.00
    iddles
    0.98
    ubb
    0.98
    Activations Density 0.009%

    No Known Activations