© 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. 3-RES-JB
    11. 8191
    Prev
    Next
    INDEX
    Explanations

    words related to suppressing or controlling something negative or undesirable

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "quit" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.71
     profession
    -0.69
    âĢ¢âĢ¢
    -0.67
     Rohing
    -0.63
    76561
    -0.61
     slee
    -0.60
     resemb
    -0.60
     Kob
    -0.59
     sag
    -0.59
     job
    -0.58
    POSITIVE LOGITS
    itely
    1.05
    rences
    0.98
    bush
    0.88
    coat
    0.83
    ocally
    0.82
    aneously
    0.82
    ilver
    0.81
    ois
    0.78
    enary
    0.75
    ilogy
    0.75
    Activations Density 0.075%

    No Known Activations