© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    statements or descriptions emphasizing power or strength

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "powerful."

    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
     Canaver
    -0.76
    chal
    -0.76
    thus
    -0.72
     Fever
    -0.71
    roma
    -0.70
     Destination
    -0.70
    arthed
    -0.68
    den
    -0.68
    ©¶æ
    -0.66
     Myster
    -0.65
    POSITIVE LOGITS
     powerful
    1.07
     chords
    0.95
    powerful
    0.89
     enough
    0.88
    iazep
    0.82
     oppress
    0.81
     hitters
    0.81
     levers
    0.78
     glim
    0.78
     intimid
    0.78
    Activations Density 0.013%

    No Known Activations