© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    words related to improvement or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    language associated with safety, improvement, and betterment

    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
    SpaceEngineers
    -0.66
     similarity
    -0.64
    utical
    -0.59
    PsyNetMessage
    -0.59
     similarities
    -0.57
    ophy
    -0.56
    alogy
    -0.55
    othing
    -0.54
    å¹
    -0.54
     hint
    -0.53
    POSITIVE LOGITS
     anew
    0.71
     territ
    0.71
    ichick
    0.67
    terday
    0.65
     ende
    0.64
    aukee
    0.64
     AGA
    0.63
    aredevil
    0.62
    cone
    0.62
    Enlarge
    0.62
    Activations Density 0.135%

    No Known Activations