© 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. 22649
    Prev
    Next
    INDEX
    Explanations

    words related to a specific entity or person, "Att"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity named "Att"

    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
    theless
    -0.84
    ktop
    -0.79
    FTWARE
    -0.76
    beard
    -0.73
    vous
    -0.73
     Cuomo
    -0.72
    士
    -0.70
    ORGE
    -0.69
    enegger
    -0.69
     Giuliani
    -0.68
    POSITIVE LOGITS
    achment
    1.24
    ainment
    1.23
    itudes
    1.22
    ractive
    1.19
    ention
    1.18
    itude
    1.17
    ension
    1.14
    itudinal
    1.13
    ributed
    1.13
    orneys
    1.11
    Activations Density 0.025%

    No Known Activations