© 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. 2149
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" indicating the presence of various subjects or actions

    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
     Telesc
    -0.76
    ossom
    -0.73
     occurs
    -0.73
    izable
    -0.73
    owan
    -0.69
    rouse
    -0.66
    ulence
    -0.66
    acters
    -0.65
     lasts
    -0.64
     entails
    -0.61
    POSITIVE LOGITS
     aware
    1.10
     willing
    1.10
     hoping
    1.10
     pleased
    1.09
     obligated
    1.07
     gearing
    1.06
     unable
    1.06
     planning
    1.05
     trying
    1.03
     preparing
    1.03
    Activations Density 0.417%

    No Known Activations