Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21941
    Prev
    Next
    INDEX
    Explanations

    words related to different countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'u'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horizont
    -0.85
    =-=-
    -0.74
    */(
    -0.73
     Attribution
    -0.72
     therap
    -0.70
     SERV
    -0.69
     Cosponsors
    -0.68
     trave
    -0.65
    milo
    -0.65
     constants
    -0.65
    POSITIVE LOGITS
    pport
    1.31
    cca
    1.17
    ccess
    1.09
    uru
    0.98
    seless
    0.97
    pta
    0.96
    isine
    0.95
    cci
    0.95
    itton
    0.95
    ji
    0.94
    Activations Density 0.028%

    No Known Activations