© 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. 21981
    Prev
    Next
    INDEX
    Explanations

    words related to growth, improvement, and advancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "develop" and its variations

    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
    zzi
    -0.81
    lua
    -0.69
    que
    -0.68
    nea
    -0.68
    wa
    -0.67
    yes
    -0.65
     Doyle
    -0.64
    tery
    -0.63
    wait
    -0.62
     disbel
    -0.62
    POSITIVE LOGITS
    iates
    0.89
    iating
    0.82
    ivities
    0.82
    irtual
    0.81
    iator
    0.80
    ivism
    0.79
    urally
    0.78
    iations
    0.76
    ement
    0.76
    mental
    0.76
    Activations Density 0.029%

    No Known Activations