© 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. 8-RES-JB
    11. 3980
    Prev
    Next
    INDEX
    Explanations

    instances of the word "resign" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resign" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĨij
    -0.71
    gran
    -0.65
    Lex
    -0.64
    rouse
    -0.62
     Reprodu
    -0.61
    ONES
    -0.61
    creation
    -0.61
    rus
    -0.60
    gat
    -0.59
    hered
    -0.58
    POSITIVE LOGITS
     resignation
    0.92
    uting
    0.91
    owship
    0.89
     resign
    0.88
     resigned
    0.87
    utes
    0.86
     abruptly
    0.83
    uted
    0.80
    utive
    0.79
    iture
    0.78
    Activations Density 0.032%

    No Known Activations