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

    Neuronpedia

    Jacobian LensNEW
    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. 20851
    Prev
    Next
    INDEX
    Explanations

    links prompting readers to share a particular story

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Share," indicating a focus on sharing actions or prompts

    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
     desper
    -0.79
    teness
    -0.76
    rift
    -0.74
     destro
    -0.74
    wagen
    -0.74
    pora
    -0.72
    vernment
    -0.72
    aternal
    -0.70
    hesda
    -0.69
    blem
    -0.69
    POSITIVE LOGITS
    UTH
    0.72
     Email
    0.72
     Share
    0.72
     PsyNet
    0.67
     Tickets
    0.64
     Print
    0.62
     Events
    0.62
    ning
    0.61
    Spons
    0.61
     Quote
    0.60
    Activations Density 0.012%

    No Known Activations