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. 10-RES-JB
    6. 2758
    Prev
    Next
    INDEX
    Explanations

    activities or actions that are performed manually, particularly using hands or feet

    oai_token-act-pair · gpt-3.5-turbo

    terms related to manual and transportation methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citiz
    -0.66
    insula
    -0.65
    ammy
    -0.65
     Tate
    -0.64
    ggles
    -0.61
    ampa
    -0.61
    eries
    -0.60
     resil
    -0.59
     Emin
    -0.58
    esta
    -0.58
    POSITIVE LOGITS
    aneously
    0.94
     rather
    0.77
     basis
    0.76
     onto
    0.76
     or
    0.70
     without
    0.69
     whereas
    0.67
     instead
    0.66
    istically
    0.66
     unless
    0.63
    Activations Density 0.338%

    No Known Activations