© 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. 10-RES-JB
    6. 1463
    Prev
    Next
    INDEX
    Explanations

    names or words related to specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azing
    -0.67
     thumbnail
    -0.59
    azes
    -0.59
     Bei
    -0.58
     adjunct
    -0.58
     approvals
    -0.56
     exception
    -0.56
     Cruiser
    -0.55
     swast
    -0.55
     judgment
    -0.55
    POSITIVE LOGITS
    cu
    1.36
    cript
    1.29
    cence
    1.25
    andro
    1.22
    cens
    1.20
    aurus
    1.18
    cue
    1.18
    ilver
    1.18
    cale
    1.17
    pring
    1.17
    Activations Density 0.101%

    No Known Activations