© 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. 20827
    Prev
    Next
    INDEX
    Explanations

    words that convey a lack of value or significance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to futility and worthlessness

    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
    orthy
    -0.83
    ebus
    -0.77
    annis
    -0.75
    asio
    -0.74
    avia
    -0.74
    artney
    -0.70
    PI
    -0.66
    uana
    -0.64
    arthy
    -0.64
    aeper
    -0.63
    POSITIVE LOGITS
     waste
    0.98
     useless
    0.83
     wastes
    0.81
     idiots
    0.80
     worthless
    0.78
    glers
    0.77
     filler
    0.77
     meaningless
    0.76
    soever
    0.75
    ãĤŃ
    0.74
    Activations Density 0.028%

    No Known Activations