© 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. 8-RES-JB
    11. 7758
    Prev
    Next
    INDEX
    Explanations

    phrases related to online activities and content

    oai_token-act-pair · gpt-3.5-turbo

    references to online activities and content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppe
    -0.69
    itar
    -0.68
    IENT
    -0.68
    chest
    -0.63
    ariat
    -0.61
     Zac
    -0.56
    eez
    -0.56
    otta
    -0.54
     Participation
    -0.53
     Nost
    -0.52
    POSITIVE LOGITS
    without
    0.81
    eatures
    0.78
    with
    0.78
    within
    0.74
    aneously
    0.73
    ilaterally
    0.72
    odon
    0.72
    abouts
    0.72
    either
    0.69
    ntil
    0.69
    Activations Density 0.121%

    No Known Activations