Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7003
    Prev
    Next
    INDEX
    Explanations

    instances of the word "benevolence"

    oai_token-act-pair · gpt-3.5-turbo

    words related to voluntary actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nest
    -0.67
     looms
    -0.67
     rake
    -0.65
     nests
    -0.63
     CTR
    -0.62
     CBD
    -0.59
     hang
    -0.58
     installed
    -0.58
     Herald
    -0.57
     Heath
    -0.56
    POSITIVE LOGITS
    vol
    4.70
    Vol
    1.98
    VOL
    1.86
     Vol
    1.56
    volent
    1.42
     VOL
    1.35
    vo
    1.28
     vol
    1.26
    volume
    1.10
    volt
    1.09
    Activations Density 0.005%

    No Known Activations