© 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. 9-RES-JB
    11. 16183
    Prev
    Next
    INDEX
    Explanations

    physical measurements and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    dimensions and measurements related to physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Renew
    -0.75
     Karma
    -0.75
     Virus
    -0.73
     virus
    -0.64
     tainted
    -0.64
    irens
    -0.63
    ourced
    -0.63
     MSG
    -0.63
     Spirits
    -0.63
     Reck
    -0.62
    POSITIVE LOGITS
     width
    1.65
     Width
    1.39
    Width
    1.38
     height
    1.31
     circumference
    1.31
     horizontal
    1.27
     horizont
    1.26
     perpendicular
    1.25
     vertical
    1.23
     angled
    1.22
    Activations Density 0.984%

    No Known Activations