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. 19167
    Prev
    Next
    INDEX
    Explanations

    phrases related to today's topics or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate group activities or collective actions

    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
    è¦ļéĨĴ
    -0.72
     informants
    -0.67
    wered
    -0.66
    ibles
    -0.63
    urat
    -0.62
    uggest
    -0.62
     ejected
    -0.62
    ById
    -0.61
    effic
    -0.61
     prophes
    -0.61
    POSITIVE LOGITS
    WE
    0.72
    SEA
    0.64
     commons
    0.63
    cele
    0.62
    namese
    0.59
    enment
    0.58
     Jas
    0.58
     news
    0.58
    paper
    0.57
    ursday
    0.56
    Activations Density 0.205%

    No Known Activations