© 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. 10-RES-JB
    11. 7265
    Prev
    Next
    INDEX
    Explanations

    news-related terms and companies

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    range
    -0.76
    interstitial
    -0.69
    adra
    -0.68
    luster
    -0.67
    optional
    -0.65
    gone
    -0.65
    stood
    -0.64
     indistinguishable
    -0.64
    depending
    -0.63
    lycer
    -0.63
    POSITIVE LOGITS
     Reporter
    1.10
     columnist
    1.09
     Editorial
    1.05
     News
    1.02
     Coverage
    1.02
     Editor
    1.02
     reporter
    1.01
     Magazine
    0.98
     Contribut
    0.98
     Staff
    0.98
    Activations Density 0.203%

    No Known Activations