© 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. 6-RES-JB
    11. 2660
    Prev
    Next
    INDEX
    Explanations

    comparisons or similarities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a sense of approximation or near-ness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oran
    -0.82
    agate
    -0.80
     Dynamics
    -0.70
    Ds
    -0.70
    oris
    -0.70
     è£ıè¦ļéĨĴ
    -0.65
    eria
    -0.65
     RTX
    -0.64
    ourses
    -0.64
    Ey
    -0.64
    POSITIVE LOGITS
     certainly
    0.80
    stress
    0.71
    etheless
    0.70
     identical
    0.70
     mundane
    0.68
    yrinth
    0.65
    rito
    0.63
    olkien
    0.63
     exclusively
    0.63
    arser
    0.63
    Activations Density 0.034%

    No Known Activations