© 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. 23827
    Prev
    Next
    INDEX
    Explanations

    mentions of strong positive sentiments like love and joy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'L' in various contexts

    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
     periodic
    -0.72
    theme
    -0.70
     mete
    -0.66
     Subtle
    -0.65
     household
    -0.63
     pony
    -0.63
     cabinet
    -0.63
     barrier
    -0.63
     Provision
    -0.62
     Prohibition
    -0.61
    POSITIVE LOGITS
    aughed
    1.41
    osing
    1.40
    aughs
    1.39
    oved
    1.38
    yrics
    1.37
    iked
    1.36
    ately
    1.35
    ousy
    1.34
    oneliness
    1.31
    oves
    1.28
    Activations Density 0.038%

    No Known Activations