© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14782
    Prev
    Next
    INDEX
    Explanations

    words related to attachment or strong connection

    oai_token-act-pair · gpt-3.5-turbo

    words related to attachment or adherence

    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
    pelling
    -0.65
     aggregation
    -0.57
    oker
    -0.57
    RFC
    -0.56
    iating
    -0.53
     Kills
    -0.53
    FK
    -0.52
     relie
    -0.51
    cloth
    -0.51
    things
    -0.50
    POSITIVE LOGITS
     thereto
    1.17
     to
    0.90
     unto
    0.88
    aciously
    0.76
    pillar
    0.75
    itionally
    0.75
     eagerly
    0.73
    To
    0.73
    ealous
    0.72
    byss
    0.71
    Activations Density 0.157%

    No Known Activations