© 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. 4-RES-JB
    11. 7597
    Prev
    Next
    INDEX
    Explanations

    words related to blaming someone or something for a particular situation or problem

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blame."

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

    No Comments

    Negative Logits
    chan
    -0.80
    forms
    -0.80
    marked
    -0.79
    spect
    -0.73
    intend
    -0.71
    irl
    -0.71
    ires
    -0.70
    quire
    -0.69
    miss
    -0.69
    ipeg
    -0.68
    POSITIVE LOGITS
     blame
    0.92
     blaming
    0.84
     blames
    0.79
     forgiven
    0.77
     Gateway
    0.68
     blamed
    0.67
     piety
    0.63
    ifully
    0.61
     accuse
    0.60
    ãĥĺ
    0.59
    Activations Density 0.016%

    No Known Activations