© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    locations or destinations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the phrase "for" in various contexts

    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
     Transcript
    -0.73
    arent
    -0.70
     implied
    -0.61
    inctions
    -0.59
    asing
    -0.59
    ased
    -0.59
     ISBN
    -0.59
    arations
    -0.58
     endings
    -0.58
     bald
    -0.58
    POSITIVE LOGITS
     sorts
    0.92
    geries
    0.83
    ENTION
    0.70
    iesta
    0.68
     excellence
    0.66
     indo
    0.64
     attracting
    0.61
    pper
    0.61
     Vit
    0.61
     discipl
    0.59
    Activations Density 0.302%

    No Known Activations