© 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. 16440
    Prev
    Next
    INDEX
    Explanations

    comparisons in size or similarity between objects

    oai_token-act-pair · gpt-3.5-turbo

    variations in size and capacity

    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
    switch
    -0.76
    ©¶æ
    -0.75
    efe
    -0.74
    cknow
    -0.68
    Switch
    -0.67
    akening
    -0.66
    spring
    -0.64
    inges
    -0.64
    kef
    -0.64
    cation
    -0.63
    POSITIVE LOGITS
     size
    1.78
     stature
    1.49
     diameter
    1.45
     length
    1.44
     quantity
    1.38
     height
    1.29
     thickness
    1.28
     sizes
    1.28
     number
    1.28
     lifespan
    1.27
    Activations Density 0.261%

    No Known Activations