© 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. 8-RES-JB
    11. 18478
    Prev
    Next
    INDEX
    Explanations

    words related to assigning responsibility or blame for certain events or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of blame or accountability in a text

    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
    estate
    -0.91
    orld
    -0.91
    esc
    -0.83
    mark
    -0.82
    intend
    -0.81
    inational
    -0.80
    edom
    -0.77
    sburg
    -0.77
    abouts
    -0.72
    conserv
    -0.72
    POSITIVE LOGITS
     inaction
    0.82
     inexper
    0.75
     blame
    0.74
     scapego
    0.70
     lax
    0.67
    ifully
    0.67
     Allaah
    0.66
     straw
    0.65
     unnamed
    0.64
     ignorance
    0.64
    Activations Density 0.043%

    No Known Activations