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. 2-RES-JB
    6. 22721
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Cleveland and its associated sports teams or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.80
    hra
    -0.65
     Mex
    -0.63
     Hath
    -0.63
    Ĭ±
    -0.62
    Else
    -0.62
    riad
    -0.61
     fam
    -0.60
     ter
    -0.60
     bowls
    -0.58
    POSITIVE LOGITS
    VEL
    1.23
    HAM
    1.05
    TAIN
    0.98
    GAN
    0.86
    ING
    0.84
    ATING
    0.84
    FORM
    0.83
    PORT
    0.81
    ocity
    0.81
    ENGTH
    0.81
    Activations Density 0.005%

    No Known Activations