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. 13711
    Prev
    Next
    INDEX
    Explanations

    C'est difficile de déterminer le critère de sélection principal pour le neurone 4 étant donné la diversité des activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation 'D.C.' or references to Washington, D.C

    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
    Maker
    -0.93
    Reviewer
    -0.80
    ãĥĨãĤ£
    -0.72
    ItemTracker
    -0.71
    ãĥŀ
    -0.70
    ãĥĻ
    -0.70
    ãĥij
    -0.68
     mats
    -0.67
    Materials
    -0.65
    éĹĺ
    -0.65
    POSITIVE LOGITS
    urry
    0.82
    .,
    0.78
    rimination
    0.78
    asse
    0.76
    ruck
    0.76
    ember
    0.75
    ollar
    0.74
    uce
    0.71
    hyde
    0.71
    isco
    0.70
    Activations Density 0.012%

    No Known Activations