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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5675
    Prev
    Next
    INDEX
    Explanations

    names of a specific person - Vicente

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "-ente," indicating nouns related to professions or statuses

    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
    acies
    -0.81
    ity
    -0.71
    acy
    -0.71
    anish
    -0.69
    dk
    -0.68
    usky
    -0.67
    rint
    -0.66
    endars
    -0.66
    ibility
    -0.65
     skelet
    -0.65
    POSITIVE LOGITS
    eers
    0.82
    chnology
    0.78
    lde
    0.74
    ignty
    0.71
    lder
    0.70
    eering
    0.68
     Barg
    0.68
    Ñģ
    0.67
     Aires
    0.66
    lda
    0.66
    Activations Density 0.063%

    No Known Activations