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

    Neuronpedia

    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. 8-RES-JB
    11. 3308
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating something is not as good or intense as something else

    oai_token-act-pair · gpt-3.5-turbo

    comparisons indicating something is not as good or effective as something else

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ����
    -0.78
    PLA
    -0.74
    DIT
    -0.70
     Limits
    -0.68
    姫
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
    timer
    -0.66
    \<
    -0.64
     [/
    -0.63
    MAP
    -0.63
    POSITIVE LOGITS
     flashy
    1.02
     glamorous
    1.01
    imilar
    0.87
     much
    0.86
     far
    0.85
     prevalent
    0.85
    fortable
    0.85
     fortunate
    0.85
     easily
    0.85
    pired
    0.84
    Activations Density 0.051%

    No Known Activations