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. 8626
    Prev
    Next
    INDEX
    Explanations

    industrial-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to industrial contexts and activities

    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
     gesture
    -0.81
     gestures
    -0.77
     cheek
    -0.77
     balls
    -0.74
    ayson
    -0.73
     flags
    -0.71
     speaker
    -0.70
     pair
    -0.69
     tears
    -0.68
     kisses
    -0.67
    POSITIVE LOGITS
    industrial
    3.40
    Indust
    2.82
    indust
    1.92
    forest
    1.25
    intel
    1.21
    workshop
    1.09
    civil
    1.08
    hospital
    1.06
     Industrial
    1.05
    SpaceEngineers
    1.04
    Activations Density 0.055%

    No Known Activations