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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17184
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to activism and activists

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of activists and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.95
    ãĤ¦ãĤ¹
    -0.81
    tains
    -0.74
    ministic
    -0.65
    fits
    -0.65
    isite
    -0.64
    ods
    -0.64
    cially
    -0.63
    lies
    -0.63
    âĶĢâĶĢâĶĢâĶĢ
    -0.63
    POSITIVE LOGITS
     celebrate
    1.15
     rejoice
    1.14
     accuse
    1.10
     unveil
    1.06
     seize
    1.05
     unite
    1.05
     gather
    1.03
     warn
    1.02
     urge
    1.01
     wrestle
    1.01
    Activations Density 0.185%

    No Known Activations