© 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. 10-RES-JB
    11. 13785
    Prev
    Next
    INDEX
    Explanations

    mentions of news media and public sentiments

    oai_token-act-pair · gpt-3.5-turbo

    references to media coverage and public commentary

    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
    NetMessage
    -0.74
    tackle
    -0.72
    heed
    -0.72
    Iterator
    -0.71
    eus
    -0.69
    ignty
    -0.68
    ococ
    -0.68
    claimer
    -0.68
    POSE
    -0.66
    atto
    -0.66
    POSITIVE LOGITS
     halls
    1.18
     fanbase
    1.12
     media
    1.11
     corridors
    1.08
     ranks
    1.02
     community
    1.02
     tabl
    1.01
     audience
    1.01
     industry
    1.00
     fandom
    1.00
    Activations Density 0.213%

    No Known Activations