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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20564
    Prev
    Next
    INDEX
    Explanations

    phrases related to apologizing and taking responsibility

    oai_token-act-pair · gpt-3.5-turbo

    language related to accountability and apologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.82
    toggle
    -0.81
    uggle
    -0.65
    ption
    -0.64
    stuff
    -0.63
    dry
    -0.63
    pop
    -0.63
     sidx
    -0.62
    ?),
    -0.62
    rez
    -0.62
    POSITIVE LOGITS
    sic
    1.11
     regrett
    1.00
     Plaintiff
    0.86
     lawful
    0.84
    Statement
    0.80
     hereby
    0.79
     inappropriate
    0.77
     Defendant
    0.76
     unlawfully
    0.76
     responsibly
    0.75
    Activations Density 1.345%

    No Known Activations