© 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. 23693
    Prev
    Next
    INDEX
    Explanations

    references to resignations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resignation."

    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
    ramid
    -0.73
    atomic
    -0.71
    hing
    -0.71
    MpServer
    -0.68
    prop
    -0.68
    ebus
    -0.67
    ohyd
    -0.65
    ramer
    -0.65
    acca
    -0.64
    verbs
    -0.64
    POSITIVE LOGITS
     resignation
    0.86
    ishment
    0.75
     announcement
    0.75
     srfAttach
    0.74
    ylum
    0.67
    cffffcc
    0.66
    anish
    0.66
    ptive
    0.64
    ptin
    0.62
     excuse
    0.60
    Activations Density 0.029%

    No Known Activations