© 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. 10200
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and organizational entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to organizations and structures

    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
     carbohyd
    -0.85
    itans
    -0.67
    amy
    -0.67
     flaming
    -0.65
    iny
    -0.65
    ilan
    -0.64
     turtle
    -0.64
    etheless
    -0.64
    ests
    -0.63
     bother
    -0.63
    POSITIVE LOGITS
     Builder
    0.98
     Integrity
    0.92
     Theatre
    0.90
     Clause
    0.89
     Depot
    0.88
     Dynamics
    0.87
     Wars
    0.87
    oft
    0.86
     Advis
    0.85
     Buildings
    0.85
    Activations Density 0.295%

    No Known Activations