© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 22852
    Prev
    Next
    INDEX
    Explanations

    phrases related to participation or activity

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location or context

    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
    wordpress
    -0.81
    aido
    -0.81
    ulet
    -0.77
    rest
    -0.71
    Ľ
    -0.68
    Ùħ
    -0.67
    founded
    -0.67
    grave
    -0.67
    gross
    -0.67
    alus
    -0.66
    POSITIVE LOGITS
    âĦ¢:
    0.68
    cation
    0.68
    ciation
    0.68
     subsequ
    0.66
     attitude
    0.66
     Activities
    0.65
    spection
    0.65
     thereto
    0.64
     kios
    0.63
    hib
    0.62
    Activations Density 0.064%

    No Known Activations