© 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. 1-RES-JB
    11. 20122
    Prev
    Next
    INDEX
    Explanations

    situations where a justification or excuse is given for certain actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deceptive justifications or rationalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omer
    -0.76
    omers
    -0.68
    irc
    -0.67
    omb
    -0.63
    devices
    -0.62
    hani
    -0.60
    itter
    -0.59
    apsed
    -0.59
    eder
    -0.59
    ECT
    -0.59
    POSITIVE LOGITS
     pretext
    1.24
    ãĥ¼ãĥĨãĤ£
    0.87
    milo
    0.86
    ual
    0.85
     excuse
    0.83
     guise
    0.81
     accuser
    0.81
    atis
    0.79
    ress
    0.78
     Tanz
    0.78
    Activations Density 0.016%

    No Known Activations