© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 24540
    Prev
    Next
    INDEX
    Explanations

    references to different types of birds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of birds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FINE
    -0.76
    xia
    -0.71
     Barnett
    -0.67
    SPONSORED
    -0.65
    NRS
    -0.64
     Cumber
    -0.63
    ahime
    -0.63
     Garc
    -0.62
    Interstitial
    -0.62
     DPR
    -0.62
    POSITIVE LOGITS
    watching
    0.96
    birds
    0.96
    seed
    0.94
    bird
    0.93
     owl
    0.91
    hawk
    0.89
    mares
    0.88
     rapt
    0.88
    ciating
    0.85
     species
    0.84
    Activations Density 0.028%

    No Known Activations