© 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. 10485
    Prev
    Next
    INDEX
    Explanations

    terms related to introducing or initiating something new

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transitioning or guiding individuals or groups

    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
    pmwiki
    -0.79
    fts
    -0.76
    ombies
    -0.75
    profits
    -0.71
    psons
    -0.66
    raid
    -0.66
    intent
    -0.66
    bia
    -0.66
     motive
    -0.65
    obbies
    -0.65
    POSITIVE LOGITS
     usher
    1.15
     ushered
    1.00
    ĸļ
    0.88
    glers
    0.84
    inson
    0.75
    hammer
    0.68
    eers
    0.67
    eering
    0.67
    illo
    0.67
    wcs
    0.65
    Activations Density 0.019%

    No Known Activations