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. 6446
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation 'AC'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "AC" related to a specific context or topic

    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
    ãĥĦ
    -0.76
     Fenrir
    -0.74
    glers
    -0.71
    ozyg
    -0.71
    doms
    -0.70
    jar
    -0.69
    lihood
    -0.68
     Tradable
    -0.68
    cake
    -0.68
    heimer
    -0.67
    POSITIVE LOGITS
    oustic
    0.98
    oust
    0.96
    ORN
    0.95
    rylic
    0.93
    CEPT
    0.87
    ros
    0.84
    upuncture
    0.83
    olor
    0.80
    HE
    0.79
    ritical
    0.79
    Activations Density 0.009%

    No Known Activations