© 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. 4-RES-JB
    11. 3609
    Prev
    Next
    INDEX
    Explanations

    words related to the term "hex"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hex colors and chemical compounds

    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
    Interstitial
    -0.94
    utenant
    -0.82
    HCR
    -0.80
    tsky
    -0.75
    jriwal
    -0.74
    ERSON
    -0.74
    OHN
    -0.72
    culosis
    -0.71
     Crowd
    -0.70
    jri
    -0.65
    POSITIVE LOGITS
    agonal
    1.40
    agon
    1.12
     hex
    1.02
    hex
    1.00
    agons
    0.91
    dump
    0.85
    agram
    0.85
    etr
    0.83
    ile
    0.82
     Hex
    0.82
    Activations Density 0.023%

    No Known Activations