© 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. 0-RES-JB
    11. 4094
    Prev
    Next
    INDEX
    Explanations

    HTML tags indicating links or buttons

    oai_token-act-pair · gpt-3.5-turbo

    HTML or XML tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offensive
    -0.60
     boycot
    -0.59
     Dund
    -0.59
     Faust
    -0.58
     needed
    -0.55
     boycott
    -0.54
     earning
    -0.54
     temporarily
    -0.54
     Falk
    -0.53
     fellow
    -0.53
    POSITIVE LOGITS
    ">
    3.74
    "><
    2.79
    "></
    2.50
    "/>
    2.50
    '>
    2.39
    \">
    2.38
    "]
    2.01
    )</
    1.88
    >"
    1.79
    </
    1.71
    Activations Density 0.009%

    No Known Activations