© 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. 22540
    Prev
    Next
    INDEX
    Explanations

    words related to challenges or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with revenge or vengeance

    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
     commodities
    -0.74
     quarters
    -0.72
     recl
    -0.69
     Long
    -0.65
     wasted
    -0.62
     iP
    -0.61
     orth
    -0.61
     PB
    -0.60
     Annotations
    -0.59
     reading
    -0.59
    POSITIVE LOGITS
    enge
    4.86
    enges
    2.80
    enged
    1.85
    enger
    1.27
    eng
    1.12
    ega
    1.01
    enne
    0.98
    onga
    0.96
    ange
    0.96
    anger
    0.92
    Activations Density 0.007%

    No Known Activations