© 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. 13835
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles or titles in a structured system or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rights and roles in a legal or business context

    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
    xious
    -0.74
    ĻĤ
    -0.70
    vice
    -0.70
    general
    -0.67
    acious
    -0.65
     bud
    -0.64
     skilled
    -0.64
    yond
    -0.64
    otte
    -0.64
     parks
    -0.64
    POSITIVE LOGITS
    âĦ¢
    1.26
     Disorder
    1.23
     Agreement
    1.15
     Award
    1.11
     Characters
    1.10
     Month
    1.10
     Period
    1.08
     Facility
    1.06
     Clause
    1.05
     Units
    1.05
    Activations Density 0.542%

    No Known Activations