© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 7302
    Prev
    Next
    INDEX
    Explanations

    words related to customization or tailoring

    oai_token-act-pair · gpt-3.5-turbo

    terms related to customization and personalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.72
     Sage
    -0.72
     Alive
    -0.67
     Plane
    -0.65
     Apostle
    -0.65
    die
    -0.65
    pg
    -0.64
    sea
    -0.63
     Apostles
    -0.63
    328
    -0.63
    POSITIVE LOGITS
     tailor
    1.32
     tailored
    1.29
    isode
    0.92
     suits
    0.91
     suit
    0.90
     corrid
    0.84
     catering
    0.81
    awaru
    0.81
    velength
    0.79
    ourgeois
    0.76
    Activations Density 0.013%

    No Known Activations