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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 114
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities related to different types of waste or substances

    oai_token-act-pair · gpt-3.5-turbo

    quantities of mass or volume related to environmental issues

    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
    gotten
    -0.76
    artist
    -0.68
    ĻĤ
    -0.66
     Atari
    -0.65
    inav
    -0.65
     pse
    -0.64
    escent
    -0.64
    Stone
    -0.62
     skelet
    -0.62
    versely
    -0.61
    POSITIVE LOGITS
    poons
    1.09
     apiece
    0.97
     worth
    0.88
     lbs
    0.88
     annually
    0.87
    pace
    0.86
     tonnes
    0.84
     barrels
    0.81
     gallons
    0.79
     pounds
    0.78
    Activations Density 0.067%

    No Known Activations