© 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. 5491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements made by sources

    oai_token-act-pair · gpt-3.5-turbo

    statements and claims made by individuals or officials regarding events or situations

    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
    ratulations
    -0.69
    ntil
    -0.65
    ptions
    -0.64
     Ammo
    -0.60
    ption
    -0.59
    estern
    -0.59
    Discussion
    -0.58
     rall
    -0.57
    Issue
    -0.56
    essen
    -0.56
    POSITIVE LOGITS
     constitutes
    1.12
     represents
    1.08
     belongs
    1.00
     ought
    0.99
     violates
    0.98
     could
    0.98
     resembles
    0.97
     constitute
    0.96
     signifies
    0.96
    could
    0.95
    Activations Density 0.140%

    No Known Activations