© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 16158
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being at halfway point

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "halfway" in various contexts

    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
    ulet
    -0.85
    UL
    -0.77
    ULE
    -0.76
    alogy
    -0.75
    urer
    -0.72
    oppable
    -0.70
    tan
    -0.69
    oran
    -0.69
    UM
    -0.69
    uci
    -0.69
    POSITIVE LOGITS
     halfway
    0.97
    terness
    0.92
    vernment
    0.72
    ï¸
    0.71
     quarters
    0.71
    assed
    0.68
    abama
    0.65
    thouse
    0.63
    phia
    0.63
     strugg
    0.63
    Activations Density 0.011%

    No Known Activations