© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 19064
    Prev
    Next
    INDEX
    Explanations

    suffixes or word endings that include 'ip'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "IP" and its variations

    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
    é¾
    -0.88
     Admir
    -0.77
     Dying
    -0.76
    âĸ¬
    -0.73
    Ùİ
    -0.73
     Aval
    -0.73
     ABE
    -0.72
     Baldwin
    -0.72
     Cause
    -0.71
     Highlander
    -0.70
    POSITIVE LOGITS
    osit
    1.19
    artisan
    1.11
    otent
    1.08
    uls
    1.07
    osite
    1.05
    ython
    1.05
    osition
    1.05
    aired
    1.05
    arent
    1.02
    rint
    1.01
    Activations Density 0.016%

    No Known Activations