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

    Neuronpedia

    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. 2-RES-JB
    11. 17697
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "blamed" followed by a reason or entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blamed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymph
    -0.83
    edom
    -0.76
    marked
    -0.75
    mental
    -0.70
    ouver
    -0.70
    birth
    -0.70
    atri
    -0.69
    inational
    -0.68
    ggies
    -0.67
    arent
    -0.66
    POSITIVE LOGITS
     blamed
    0.94
     blames
    0.87
     blame
    0.84
     scapego
    0.79
     blaming
    0.79
     forgiven
    0.77
     attribut
    0.70
    ãĤ¼
    0.69
     culprit
    0.67
     victim
    0.66
    Activations Density 0.006%

    No Known Activations