© 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. 1-RES-JB
    11. 24150
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a deliberate choice to disregard or overlook something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ignore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramer
    -0.93
    unal
    -0.92
    uliffe
    -0.86
    emetery
    -0.81
    arter
    -0.80
    alg
    -0.75
    urther
    -0.74
    gran
    -0.74
    aver
    -0.73
    raq
    -0.73
    POSITIVE LOGITS
     ignore
    0.89
     ignores
    0.82
     ignoring
    0.74
     underestimate
    0.73
     aside
    0.72
     overlook
    0.72
     ignored
    0.71
    fulness
    0.70
     neglect
    0.68
     obe
    0.65
    Activations Density 0.012%

    No Known Activations