© 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. 19264
    Prev
    Next
    INDEX
    Explanations

    words related to writing activities or content creation

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing written works or documents

    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
     granted
    -0.71
    seekers
    -0.71
    ONSORED
    -0.71
    ão
    -0.68
    kat
    -0.64
    assetsadobe
    -0.63
     hunters
    -0.63
    enance
    -0.63
    fal
    -0.62
    Hung
    -0.62
    POSITIVE LOGITS
     screenplay
    1.03
     diary
    0.93
     memoir
    0.89
     autobiography
    0.88
     blog
    0.88
     poem
    0.86
     letter
    0.84
     poems
    0.84
     poetry
    0.83
     journal
    0.81
    Activations Density 0.159%

    No Known Activations