© 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. 8-RES-JB
    11. 19363
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attributions or blaming someone or something for a particular event or outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating attribution or blame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efer
    -0.88
    apest
    -0.86
    ensable
    -0.80
    ŃĶ
    -0.77
    ourse
    -0.76
    ela
    -0.75
    utsche
    -0.74
    imensional
    -0.73
    apolis
    -0.73
    raf
    -0.72
    POSITIVE LOGITS
     inexper
    1.13
     incompetence
    1.06
     negligence
    1.03
     faulty
    1.02
     lack
    0.92
     boredom
    0.91
     misunderstanding
    0.90
     inaction
    0.90
     coincidence
    0.89
     factors
    0.89
    Activations Density 0.483%

    No Known Activations