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. 9-RES-JB
    6. 12172
    Prev
    Next
    INDEX
    Explanations

    words related to dirtiness or degradation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "gr," particularly in a context of describing negative traits or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.73
     Kund
    -0.71
    fixed
    -0.62
    dating
    -0.62
    ership
    -0.61
     Doctrine
    -0.61
     Mn
    -0.59
     fund
    -0.59
    ãĥ´ãĤ¡
    -0.58
    doors
    -0.58
    POSITIVE LOGITS
    udge
    1.26
    udging
    1.22
    umpy
    1.22
    iddles
    1.06
    aciously
    1.04
    iddle
    1.03
    ubby
    1.03
    iffin
    1.01
    aced
    1.01
    itt
    0.99
    Activations Density 0.022%

    No Known Activations