© 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. 9-RES-JB
    11. 8682
    Prev
    Next
    INDEX
    Explanations

    words related to organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    plural noun forms pertaining to characters, entities, or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASED
    -0.69
     srfAttach
    -0.68
    ABLE
    -0.64
     carbohyd
    -0.63
     dissemination
    -0.61
    PDATE
    -0.60
     newsp
    -0.59
    MENTS
    -0.58
     exha
    -0.58
     proble
    -0.58
    POSITIVE LOGITS
    mith
    1.61
    aurus
    1.55
    peed
    1.37
    ilver
    1.33
    hip
    1.33
    kaya
    1.31
    ystem
    1.28
    cale
    1.27
    peak
    1.26
    poon
    1.25
    Activations Density 0.273%

    No Known Activations