© 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. 0-RES-JB
    11. 22510
    Prev
    Next
    INDEX
    Explanations

    strategies or tactics mentioned within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to various strategies being implemented or discussed

    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
    brance
    -0.79
    ouple
    -0.68
    head
    -0.67
     behold
    -0.65
    nder
    -0.65
     ransom
    -0.63
    iam
    -0.61
     dock
    -0.61
     Flesh
    -0.60
    roma
    -0.60
    POSITIVE LOGITS
     strategies
    3.19
     Strategies
    2.15
     techniques
    1.91
     tactics
    1.77
     methods
    1.75
     behaviors
    1.66
     approaches
    1.59
     solutions
    1.58
     mechanisms
    1.58
     theories
    1.57
    Activations Density 0.014%

    No Known Activations