© 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. 8-RES-JB
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    words related to development and progress

    oai_token-act-pair · gpt-3.5-turbo

    references to development topics

    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
    zzi
    -1.01
    pload
    -0.80
    asus
    -0.80
    Ń·
    -0.77
    akia
    -0.75
    duty
    -0.68
    verages
    -0.67
    haul
    -0.66
    ENA
    -0.65
    ighed
    -0.65
    POSITIVE LOGITS
    ally
    1.07
    ivism
    0.84
     Goals
    0.83
    ively
    0.82
    hower
    0.74
     Pione
    0.74
    ional
    0.72
    iator
    0.71
    mental
    0.69
    ivist
    0.69
    Activations Density 0.046%

    No Known Activations