© 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. 4937
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases that indicate possession or association

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote possession or belonging

    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
    dayName
    -0.76
     disposed
    -0.63
    assembly
    -0.60
    eele
    -0.59
    illac
    -0.59
     condem
    -0.58
    irs
    -0.58
    blance
    -0.56
    Battery
    -0.56
     redesign
    -0.56
    POSITIVE LOGITS
     sudden
    0.79
    THING
    0.78
     humanity
    0.70
     us
    0.69
    llor
    0.68
    udes
    0.64
    ahu
    0.64
     humankind
    0.63
    those
    0.62
    ooting
    0.61
    Activations Density 0.060%

    No Known Activations