© 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. 18733
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or functions performed by objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of entities or concepts described as playing active or representative roles

    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
    chev
    -0.74
    rants
    -0.70
    rone
    -0.70
    eor
    -0.68
    ties
    -0.66
    olds
    -0.66
    tten
    -0.65
    tom
    -0.64
    yd
    -0.64
    ulous
    -0.63
    POSITIVE LOGITS
     intermediary
    1.13
     liaison
    0.96
     catalyst
    0.94
     deterrent
    0.94
     conduit
    0.92
     lookout
    0.92
     intermedi
    0.91
     condu
    0.88
     interpreter
    0.88
     surrogate
    0.86
    Activations Density 0.081%

    No Known Activations