© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12878
    Prev
    Next
    INDEX
    Explanations

    phrases related to feeling comfortable in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to feelings of comfort and discomfort in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.89
    ector
    -0.76
    olitics
    -0.73
    actionDate
    -0.72
    aic
    -0.71
    ISE
    -0.71
    Asia
    -0.67
    ledged
    -0.66
    vantage
    -0.65
    ENCE
    -0.65
    POSITIVE LOGITS
     putting
    1.38
     doing
    1.36
     messing
    1.36
     handing
    1.35
     deleting
    1.35
     executing
    1.34
     inserting
    1.33
     treating
    1.32
     installing
    1.31
     letting
    1.31
    Activations Density 0.654%

    No Known Activations