© 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. 1-RES-JB
    6. 7008
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific text or library

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "text" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.81
    pload
    -0.71
     Forbes
    -0.70
    thur
    -0.68
     solitary
    -0.67
    vernment
    -0.67
     balcony
    -0.66
    Downloadha
    -0.64
     capita
    -0.63
    keley
    -0.63
    POSITIVE LOGITS
    text
    1.10
    uality
    1.07
     Text
    1.06
    ual
    1.05
    ured
    1.01
    escription
    0.97
    TEXT
    0.94
    ures
    0.93
    Text
    0.91
    icons
    0.88
    Activations Density 0.010%

    No Known Activations