© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6560
    Prev
    Next
    INDEX
    Explanations

    words related to digital technology and currencies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of digital concepts and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.89
    etta
    -0.80
    etts
    -0.79
    ortium
    -0.79
    pell
    -0.75
    hov
    -0.75
    els
    -0.74
    ered
    -0.69
     Strauss
    -0.68
    olini
    -0.68
    POSITIVE LOGITS
    Ocean
    1.10
    ized
    0.96
     nom
    0.94
    isation
    0.91
    izable
    0.91
     currencies
    0.90
     currency
    0.90
    ization
    0.90
     footprint
    0.86
     natives
    0.85
    Activations Density 0.032%

    No Known Activations