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. 11-RES-JB
    6. 4673
    Prev
    Next
    INDEX
    Explanations

    descriptive words and phrases related to unique and remarkable locations or places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bots
    -0.96
     Freddy
    -0.83
    girls
    -0.78
    aughs
    -0.77
    Tickets
    -0.77
     Agents
    -0.76
    ©¶æ
    -0.75
    Attach
    -0.75
    mails
    -0.74
    Aud
    -0.73
    POSITIVE LOGITS
     geological
    1.44
     basin
    1.38
     mountainous
    1.37
     volcanic
    1.33
     region
    1.29
     continent
    1.27
     plateau
    1.26
     coastline
    1.25
     peninsula
    1.22
     UNESCO
    1.20
    Activations Density 0.293%

    No Known Activations