© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    words related to SegWit (Segregated Witness) technology and its implementations

    oai_token-act-pair · gpt-3.5-turbo

    references to segments of a network in a blockchain context

    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
    oker
    -0.78
    iating
    -0.75
    isher
    -0.72
    iate
    -0.71
     indo
    -0.71
    ity
    -0.71
    ashtra
    -0.71
    ichita
    -0.69
    iar
    -0.68
     Seym
    -0.68
    POSITIVE LOGITS
     eclipse
    0.98
     Seg
    0.86
    gments
    0.81
    lease
    0.81
    âĶĢâĶĢâĶĢâĶĢ
    0.78
    Seg
    0.75
    İĭ
    0.72
    geist
    0.72
    way
    0.70
    mented
    0.70
    Activations Density 0.051%

    No Known Activations