© 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. 7-RES-JB
    11. 23494
    Prev
    Next
    INDEX
    Explanations

    the word "Horace" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Horace."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.76
    ãģ¦
    -0.76
    anwhile
    -0.72
    ãģ®éŃĶ
    -0.71
    0000000000000000
    -0.67
     succeeding
    -0.66
     Leilan
    -0.65
    enhagen
    -0.64
     graded
    -0.62
    conservancy
    -0.61
    POSITIVE LOGITS
    izontal
    1.43
    izont
    1.38
    izons
    1.27
    rible
    1.27
    ror
    1.15
    ribly
    1.14
    izon
    1.13
    rors
    1.09
    cru
    1.08
    oscope
    1.06
    Activations Density 0.026%

    No Known Activations