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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1655
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to capacity, speed, brightness, intensity, altitude, and resolution

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and measurements related to capacity, speed, and performance

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

    No Comments

    Negative Logits
    alus
    -0.89
    itled
    -0.84
    bara
    -0.80
    roman
    -0.78
    eyes
    -0.78
    romy
    -0.77
    roma
    -0.76
    ullivan
    -0.75
    odon
    -0.73
    gres
    -0.72
    POSITIVE LOGITS
     ranges
    0.99
     difference
    0.94
     coefficient
    0.94
     ratio
    0.89
     range
    0.89
     tolerance
    0.88
     differential
    0.85
     gradient
    0.82
     threshold
    0.81
     extremes
    0.81
    Activations Density 0.155%

    No Known Activations