© 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. 7-RES-JB
    6. 5311
    Prev
    Next
    INDEX
    Explanations

    the name "Ch" followed by a number (e.g., Ch9, Ch10) in a text

    oai_token-act-pair · gpt-3.5-turbo

    specific character references or names in texts

    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
    WARD
    -0.77
     lockout
    -0.73
    ITED
    -0.70
     visitation
    -0.66
     "$:/
    -0.66
    PORT
    -0.65
     Reloaded
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.63
    FORMATION
    -0.63
    ãĤ´ãĥ³
    -0.62
    POSITIVE LOGITS
    amps
    1.21
    aos
    1.17
    isel
    1.17
    orus
    1.16
    unks
    1.16
    ieft
    1.12
    ivalry
    1.12
    annels
    1.11
    illing
    1.11
    ubby
    1.10
    Activations Density 0.033%

    No Known Activations