© 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. 4-RES-JB
    11. 24440
    Prev
    Next
    INDEX
    Explanations

    terms related to data and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with analytics and data analysis

    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
    hood
    -0.75
    ifest
    -0.74
    liness
    -0.74
    birth
    -0.71
    nered
    -0.69
    eem
    -0.68
    INGS
    -0.68
    ength
    -0.68
    lain
    -0.66
    adder
    -0.66
    POSITIVE LOGITS
     analytics
    1.09
     dashboard
    0.85
     Analytics
    0.76
    avascript
    0.72
    urus
    0.72
    analy
    0.71
    herer
    0.69
     methodology
    0.68
     compute
    0.68
     metrics
    0.67
    Activations Density 0.020%

    No Known Activations