© 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. 4-RES-JB
    11. 15849
    Prev
    Next
    INDEX
    Explanations

    quantitative data presented as percentages or points

    oai_token-act-pair · gpt-3.5-turbo

    references to percentage points in statistical data

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

    No Comments

    Negative Logits
    ufact
    -0.83
    uthor
    -0.79
     tremend
    -0.67
    RAW
    -0.66
     garg
    -0.65
    æĸ¹
    -0.64
    cular
    -0.64
    ACTION
    -0.62
    ItemTracker
    -0.62
    rodu
    -0.61
    POSITIVE LOGITS
     points
    0.80
    lash
    0.80
    point
    0.77
     (+
    0.74
    points
    0.72
     Amendments
    0.70
     blank
    0.67
    itched
    0.67
     squared
    0.66
    ochet
    0.66
    Activations Density 0.016%

    No Known Activations