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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 14219
    Prev
    Next
    INDEX
    Explanations

    phrases related to a coming together or joining of different entities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to change and transformation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verbs
    -0.74
    otrop
    -0.73
    olesterol
    -0.70
    enced
    -0.70
    ¯¯
    -0.70
    rib
    -0.69
    rol
    -0.67
    othes
    -0.66
    Ingredients
    -0.65
    iencies
    -0.64
    POSITIVE LOGITS
    xual
    0.91
     thereof
    0.85
     mathemat
    0.84
     convergence
    0.80
     divergence
    0.78
     ende
    0.75
     nexus
    0.74
     stemming
    0.74
     rate
    0.73
     avoidance
    0.73
    Activations Density 0.069%

    No Known Activations