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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11107
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical engineering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanical engineering

    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
     Beir
    -0.84
     Bundy
    -0.73
     Ireland
    -0.72
     Views
    -0.72
    pak
    -0.71
     Tuls
    -0.71
     Uganda
    -0.70
    ense
    -0.69
    AIDS
    -0.69
     Assets
    -0.69
    POSITIVE LOGITS
     mechanical
    3.55
     Mechanical
    2.32
     mechanically
    2.16
     robotic
    1.56
    Mech
    1.55
     hydraulic
    1.53
     mechan
    1.50
     mechanics
    1.47
     electrical
    1.42
     mechanic
    1.41
    Activations Density 0.026%

    No Known Activations