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. 2603
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical interaction or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical interactions or contact with surfaces

    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
    ãĤ´ãĥ³
    -0.77
    ruary
    -0.76
    href
    -0.76
     Nationwide
    -0.74
    yssey
    -0.69
    Calif
    -0.66
    hra
    -0.66
    Translation
    -0.65
    Recomm
    -0.65
    show
    -0.65
    POSITIVE LOGITS
     surfaces
    1.44
     unsuspecting
    1.38
     objects
    1.34
     targets
    1.13
     walls
    1.06
     surface
    1.06
     target
    1.05
     Objects
    1.04
    objects
    1.02
     fabrics
    1.01
    Activations Density 0.281%

    No Known Activations