Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14870
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of devolution

    oai_token-act-pair · gpt-3.5-turbo

    words related to development and political evolution

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

    No Comments

    Negative Logits
    TPS
    -0.86
     Jill
    -0.71
     Tess
    -0.68
     Dos
    -0.66
     FIGHT
    -0.66
     Fight
    -0.66
     Aj
    -0.65
     Ana
    -0.63
     Die
    -0.63
     Ta
    -0.62
    POSITIVE LOGITS
    interstitial
    0.91
    ciating
    0.87
    merce
    0.84
    minist
    0.82
    cipline
    0.81
    olved
    0.79
    estate
    0.78
     satell
    0.75
     discretionary
    0.75
     legislatures
    0.74
    Activations Density 0.022%

    No Known Activations