© 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. 14745
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a resolution or conclusion, with a focus on the concept of determination and inevitability

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or phrases indicating questions about conditions or situations

    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
    ãĥį
    -0.83
     Uriel
    -0.76
    ãĥĨ
    -0.75
    ãĥ¯
    -0.75
    ãĤ¿
    -0.74
    idel
    -0.74
    lyak
    -0.73
    Afee
    -0.70
    alk
    -0.70
    aeda
    -0.69
    POSITIVE LOGITS
     whatsoever
    0.84
     slightest
    0.74
     jurisdiction
    0.72
     severity
    0.70
     depended
    0.70
     thickness
    0.68
     bothers
    0.68
     encount
    0.68
     anymore
    0.67
     challeng
    0.67
    Activations Density 0.046%

    No Known Activations