© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific processes or technical actions

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to evidence and documentation

    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
     ?)
    -1.02
    )?
    -0.99
    ?]
    -0.88
    ?),
    -0.82
    ?)
    -0.82
    ?",
    -0.77
    "?
    -0.75
    ?).
    -0.74
    ?ãĢį
    -0.73
    ?'
    -0.71
    POSITIVE LOGITS
    .
    0.69
     revealing
    0.66
     allowing
    0.64
     indicating
    0.64
     demonstrating
    0.60
     informing
    0.59
     whereby
    0.59
     ensuring
    0.58
     overshadow
    0.57
     totaling
    0.57
    Activations Density 1.376%

    No Known Activations