© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 24220
    Prev
    Next
    INDEX
    Explanations

    terms related to awe and wonder

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender, specifically emphasizing the concept of "woman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.63
    packing
    -0.61
     screen
    -0.60
     ENTER
    -0.60
     Hampton
    -0.59
    OUT
    -0.59
    sheet
    -0.57
    https
    -0.57
     pasture
    -0.56
     Beautiful
    -0.56
    POSITIVE LOGITS
    omen
    1.26
    ovic
    0.86
    stru
    0.85
    oshenko
    0.84
    opol
    0.83
    nant
    0.83
    oso
    0.83
    eday
    0.82
    iak
    0.81
    nown
    0.81
    Activations Density 0.005%

    No Known Activations