© 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. 8-RES-JB
    11. 6947
    Prev
    Next
    INDEX
    Explanations

    sequences of symbols like codes or commands, highlighted by the presence of specific characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of certain indicators or prompts for additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -1.02
    etheless
    -0.93
    yssey
    -0.90
     nodd
    -0.82
    onial
    -0.82
    entimes
    -0.82
    ModLoader
    -0.78
     neighb
    -0.77
    erville
    -0.76
    teenth
    -0.76
    POSITIVE LOGITS
    _>
    1.35
    =>
    0.88
    ++++
    0.83
    PsyNetMessage
    0.76
    .<
    0.72
     >
    0.71
    ALL
    0.70
    RO
    0.66
    TPS
    0.65
    âĸĴ
    0.64
    Activations Density 0.019%

    No Known Activations