© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2690
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the use of objects or concepts for specific purposes

    oai_token-act-pair · gpt-3.5-turbo

    articles and phrases that imply the use of something as a tool or mechanism

    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
    akis
    -0.77
    ichen
    -0.74
    events
    -0.72
    views
    -0.72
    ents
    -0.72
    doms
    -0.71
    lees
    -0.71
    cies
    -0.70
    reys
    -0.70
    oried
    -0.70
    POSITIVE LOGITS
     substitute
    1.17
     basis
    1.14
     guide
    1.14
     deterrent
    1.12
     backdrop
    1.10
     placeholder
    1.09
     conduit
    1.06
     complement
    1.05
     surrogate
    1.05
     catalyst
    1.05
    Activations Density 0.151%

    No Known Activations