© 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. 10-RES-JB
    11. 14044
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical characteristics of objects, particularly focusing on material and build quality

    oai_token-act-pair · gpt-3.5-turbo

    features and specifications of electronic devices

    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
    ewitness
    -0.93
    aunder
    -0.80
     Cooperative
    -0.75
    nesday
    -0.75
    #$#$
    -0.73
    glers
    -0.73
    agents
    -0.72
    weekly
    -0.71
     contag
    -0.71
    opathic
    -0.69
    POSITIVE LOGITS
     chassis
    1.53
     specs
    1.34
     sleek
    1.31
     aluminium
    1.25
     aluminum
    1.21
     styling
    1.20
     chipset
    1.17
     matte
    1.17
     specifications
    1.13
     design
    1.12
    Activations Density 0.365%

    No Known Activations