© 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. 0-RES-JB
    11. 13887
    Prev
    Next
    INDEX
    Explanations

    phrases related to inhaling or concealing

    oai_token-act-pair · gpt-3.5-turbo

    words related to concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsigned
    -0.68
     credit
    -0.59
    void
    -0.59
     creed
    -0.58
     opinions
    -0.57
     Lords
    -0.55
     conceptions
    -0.55
     voic
    -0.54
     Symphony
    -0.54
     prose
    -0.53
    POSITIVE LOGITS
    aling
    4.31
    aled
    2.89
    aler
    2.27
    alling
    2.23
    ales
    1.79
    als
    1.78
    alled
    1.55
    ale
    1.50
    al
    1.46
    ALE
    1.23
    Activations Density 0.011%

    No Known Activations