© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3405
    Prev
    Next
    INDEX
    Explanations

    specific instructions or recommendations related to physical objects or activities, particularly regarding alignment or positioning

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guidelines related to physical structures and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Online
    -0.72
    Daily
    -0.71
    Politics
    -0.69
    Rum
    -0.67
    Terror
    -0.65
    puters
    -0.65
    Nation
    -0.64
    MQ
    -0.63
     Rwanda
    -0.61
    Money
    -0.61
    POSITIVE LOGITS
     protr
    1.42
     thickness
    1.34
     diameter
    1.26
     seams
    1.25
     width
    1.24
     indent
    1.23
     circumference
    1.22
     perpendicular
    1.22
     angled
    1.17
     hinge
    1.16
    Activations Density 0.728%

    No Known Activations