© 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. 9378
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "from."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "from."

    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
    KK
    -0.82
    anim
    -0.81
    ratulations
    -0.81
    numbered
    -0.78
    motion
    -0.75
    pressure
    -0.74
    Speed
    -0.73
    airs
    -0.72
    amiya
    -0.72
    ICA
    -0.71
    POSITIVE LOGITS
     afar
    1.18
     whence
    1.00
     thence
    0.99
     somewhere
    0.96
     scratch
    0.92
     abroad
    0.90
     everywhere
    0.83
     atop
    0.79
     wherever
    0.77
     elsewhere
    0.76
    Activations Density 0.100%

    No Known Activations