© 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. 4-RES-JB
    11. 8606
    Prev
    Next
    INDEX
    Explanations

    references to news and media outlets, particularly "HuffPost" and "Vox"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific media outlets, particularly "HuffPost" and "Vox"

    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
    BuyableInstoreAndOnline
    -0.74
    ========
    -0.68
    ============
    -0.65
    arters
    -0.63
     retri
    -0.62
     sophistication
    -0.61
    creen
    -0.59
    backs
    -0.59
    displayText
    -0.59
    gio
    -0.58
    POSITIVE LOGITS
    edIn
    0.95
     HuffPost
    0.84
    shire
    0.81
    odox
    0.79
    icity
    0.76
    entimes
    0.75
    ileaks
    0.74
    ioned
    0.70
    Politics
    0.70
    igen
    0.69
    Activations Density 0.008%

    No Known Activations