© 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. 4-RES-JB
    6. 10526
    Prev
    Next
    INDEX
    Explanations

    sentences instructing to read more on a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    references to reading-related actions or discussions

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

    No Comments

    Negative Logits
    oult
    -0.75
    TEXTURE
    -0.70
    ascal
    -0.68
    cffffcc
    -0.66
     heel
    -0.66
     USSR
    -0.63
    aviour
    -0.62
    pload
    -0.62
    VP
    -0.61
     WWF
    -0.61
    POSITIVE LOGITS
    Write
    0.96
     aloud
    0.90
    Read
    0.86
    just
    0.81
    ahead
    0.81
    gon
    0.79
    iances
    0.79
    dress
    0.78
     Continued
    0.76
     Read
    0.75
    Activations Density 0.019%

    No Known Activations