Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 87
    Prev
    Next
    INDEX
    Explanations

    words related to blaming someone or something for a certain situation or outcome

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blame."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word 'blame'

    oai_token-act-pair · gpt-4-turbo
    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
    ires
    -0.74
    irl
    -0.74
    marked
    -0.72
    inational
    -0.71
    forms
    -0.70
    raised
    -0.69
    afort
    -0.67
    emale
    -0.65
    chan
    -0.65
    ammy
    -0.65
    POSITIVE LOGITS
     blame
    1.19
     blames
    0.91
     blamed
    0.85
     blaming
    0.85
     forgiven
    0.79
     attribut
    0.76
     forgiveness
    0.71
     culprit
    0.70
    ãĥĥãĥī
    0.69
     accuse
    0.68
    Activations Density 0.014%

    No Known Activations