© 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. 6265
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas and quotation marks

    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
    ratulations
    -0.64
    çīĪ
    -0.62
    ixt
    -0.62
    ominated
    -0.59
    aimon
    -0.56
    robat
    -0.56
    rament
    -0.56
    rius
    -0.55
     seiz
    -0.55
    !'
    -0.55
    POSITIVE LOGITS
     noting
    1.15
     citing
    1.02
     adding
    1.02
     implying
    1.00
     namely
    0.99
     although
    0.96
     stressing
    0.93
     including
    0.92
     whereas
    0.91
    including
    0.91
    Activations Density 0.463%

    No Known Activations