© 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. 0-RES-JB
    11. 20455
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms beginning with 'RS'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regulatory standards and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.90
    conom
    -0.87
    Cola
    -0.85
     Zup
    -0.84
    à¨
    -0.83
    âĶĢâĶĢâĶĢâĶĢ
    -0.82
    avery
    -0.80
    aphael
    -0.80
    alus
    -0.78
    Newsletter
    -0.77
    POSITIVE LOGITS
     LR
    2.15
     RS
    2.01
     TT
    2.00
     RL
    1.98
     RC
    1.95
     HS
    1.93
     RD
    1.92
     HC
    1.90
     GD
    1.90
     HL
    1.89
    Activations Density 0.072%

    No Known Activations