© 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. 11-RES-JB
    11. 9949
    Prev
    Next
    INDEX
    Explanations

    phrases containing the expression "used to."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express past habits or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oval
    -0.80
    IDA
    -0.72
    edIn
    -0.71
    ð
    -0.71
    unal
    -0.70
    ares
    -0.69
     Expansion
    -0.67
    impro
    -0.65
    soever
    -0.65
    leaf
    -0.64
    POSITIVE LOGITS
     joke
    1.15
     haunt
    1.01
     tease
    0.95
     be
    0.92
     adore
    0.90
     roam
    0.89
     flock
    0.88
     hate
    0.87
     dominate
    0.87
     laugh
    0.86
    Activations Density 0.059%

    No Known Activations