© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9834
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people

    oai_token-act-pair · gpt-3.5-turbo

    references to brand names or notable figures associated with chocolate products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamp
    -0.85
    arters
    -0.82
    mercial
    -0.81
    izable
    -0.70
    RAFT
    -0.66
     Honolulu
    -0.65
     Cancel
    -0.63
    izoph
    -0.62
     Mirage
    -0.62
    atable
    -0.62
    POSITIVE LOGITS
    heastern
    1.01
    lessly
    0.96
    heast
    0.80
    hey
    0.76
    lect
    0.73
    hest
    0.72
    earcher
    0.71
    wit
    0.71
    hus
    0.70
    rely
    0.70
    Activations Density 0.076%

    No Known Activations