© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1630
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to the concept of 'broad'

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with inclusivity and generality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.77
    ILLE
    -0.77
     Keeper
    -0.73
    ICAN
    -0.72
    LV
    -0.72
     Million
    -0.67
    Dialogue
    -0.66
     Camer
    -0.63
     Disciple
    -0.63
    Fight
    -0.62
    POSITIVE LOGITS
    sheet
    1.56
    sheets
    1.37
    ening
    1.26
    sword
    1.13
    leaf
    1.13
    ened
    1.03
     strokes
    1.02
     spectrum
    0.99
    side
    0.94
    cloth
    0.94
    Activations Density 0.025%

    No Known Activations