© 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. 2-RES-JB
    11. 11284
    Prev
    Next
    INDEX
    Explanations

    references to file sizes, specifically in terms of MB

    oai_token-act-pair · gpt-3.5-turbo

    references to memory capacity measurements in megabytes (MB)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zona
    -0.73
     Lawn
    -0.64
    cha
    -0.63
    kies
    -0.62
     Akron
    -0.61
    ×Ļ×
    -0.61
     median
    -0.60
     Gors
    -0.59
     pol
    -0.59
    ×ķ
    -0.59
    POSITIVE LOGITS
    MB
    0.92
    ishop
    0.91
    utable
    0.84
    emonic
    0.82
    TeX
    0.81
    aton
    0.81
    uilt
    0.80
    uild
    0.80
    KK
    0.79
    ilit
    0.78
    Activations Density 0.006%

    No Known Activations