© 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. 7-RES-JB
    11. 9829
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical events and international relations

    oai_token-act-pair · gpt-3.5-turbo

    punctuated transitions and modifiers in complex statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eus
    -0.80
    cell
    -0.72
    sylv
    -0.70
    xxxx
    -0.69
    pole
    -0.69
    iple
    -0.68
    uscript
    -0.67
    mons
    -0.66
    enth
    -0.66
    isle
    -0.65
    POSITIVE LOGITS
     prompting
    1.10
     including
    1.05
     citing
    1.03
     fuelled
    0.96
     sparking
    0.94
     stemming
    0.94
     culminating
    0.94
     fearing
    0.93
     bolstered
    0.92
     spurred
    0.90
    Activations Density 0.478%

    No Known Activations