© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth and development

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to growth and increase

    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
    soDeliveryDate
    -0.75
     Hague
    -0.71
     principals
    -0.66
    ãĥīãĥ©
    -0.66
    querque
    -0.65
    fax
    -0.64
    £ı
    -0.61
     Keyboard
    -0.59
     Guerrero
    -0.59
    ij士
    -0.58
    POSITIVE LOGITS
     leaps
    0.93
     exponentially
    0.93
     stature
    0.86
     explos
    0.73
     maturity
    0.70
    atten
    0.70
     Slowly
    0.66
    ustomed
    0.66
     tentacles
    0.66
    /+
    0.65
    Activations Density 0.233%

    No Known Activations