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. 8-RES-JB
    6. 23154
    Prev
    Next
    INDEX
    Explanations

    personal statements or self-descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" and the pronoun "I"

    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
     bearer
    -0.77
    bda
    -0.74
     denomin
    -0.71
     casualty
    -0.68
     accompanies
    -0.68
     territ
    -0.68
     monop
    -0.67
    agues
    -0.66
     resorts
    -0.66
     athlet
    -0.65
    POSITIVE LOGITS
    rael
    0.81
     gonna
    0.81
    Pak
    0.81
    orno
    0.80
    Shield
    0.77
    kaya
    0.71
    Ô
    0.71
    uala
    0.71
     Been
    0.70
    Interest
    0.69
    Activations Density 0.148%

    No Known Activations