© 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. 8-RES-JB
    11. 24005
    Prev
    Next
    INDEX
    Explanations

    words related to news or media

    oai_token-act-pair · gpt-3.5-turbo

    words related to news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asse
    -0.76
    ayne
    -0.74
    inho
    -0.70
     Wade
    -0.67
     Ernst
    -0.65
     defective
    -0.65
    inished
    -0.65
    ersen
    -0.64
     Scher
    -0.63
     Lak
    -0.63
    POSITIVE LOGITS
    worthy
    1.10
    feed
    1.07
    room
    1.01
    reader
    0.98
    flash
    0.96
    rooms
    0.96
     headlines
    0.96
    worthiness
    0.94
    groups
    0.93
    orial
    0.91
    Activations Density 0.051%

    No Known Activations