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. 4-RES-JB
    6. 3483
    Prev
    Next
    INDEX
    Explanations

    words related to 'ip' or 'ip' with a specific number as prefix

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ip" and its variations, likely indicating a focus on Internet Protocol or related technical terminology

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

    No Comments

    Negative Logits
    é¾
    -0.79
    DERR
    -0.79
     Dying
    -0.78
     EntityItem
    -0.73
     Admir
    -0.70
     Aval
    -0.68
     Angels
    -0.67
    DEV
    -0.66
     Horizon
    -0.65
    âĸ¬
    -0.65
    POSITIVE LOGITS
    osit
    1.24
    otent
    1.17
    artisan
    1.13
    arent
    1.08
    osition
    1.07
    ython
    1.04
    roxy
    1.03
    aired
    1.02
    inion
    1.01
    uls
    1.01
    Activations Density 0.017%

    No Known Activations