© 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. 7-RES-JB
    11. 12505
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms related to software development

    oai_token-act-pair · gpt-3.5-turbo

    programming or coding parameters and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bush
    -0.60
     karma
    -0.58
     tolerant
    -0.58
     outweigh
    -0.54
     softened
    -0.54
     tending
    -0.54
    _-
    -0.53
     shr
    -0.53
     Goodell
    -0.53
     plural
    -0.52
    POSITIVE LOGITS
    utils
    0.81
    roma
    0.79
    thora
    0.78
    racuse
    0.69
    interstitial
    0.67
    icio
    0.66
    ulative
    0.64
    Storage
    0.64
    onz
    0.63
    okers
    0.62
    Activations Density 0.207%

    No Known Activations