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. 12-RES-JB
    6. 14559
    Prev
    Next
    INDEX
    Explanations

    references to the geopolitical location Djibouti and individuals related to it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the name "Gu"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     interchangeable
    -0.83
     mete
    -0.72
     disparate
    -0.65
     replacements
    -0.65
     spaced
    -0.65
     squares
    -0.64
     alarms
    -0.64
     starting
    -0.64
     genetics
    -0.63
     bearer
    -0.63
    POSITIVE LOGITS
    errilla
    1.47
    itars
    1.37
    cci
    1.36
    adal
    1.36
    bernatorial
    1.34
    iller
    1.32
    zman
    1.31
    ido
    1.30
    vernment
    1.21
    ided
    1.18
    Activations Density 0.010%

    No Known Activations