© 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. 9-RES-JB
    11. 5318
    Prev
    Next
    INDEX
    Explanations

    mentions of Ayn Rand or related concepts like altruism and greed

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flip
    -0.66
     Solitaire
    -0.66
     overweight
    -0.65
    hole
    -0.64
     fuzz
    -0.63
    unin
    -0.63
    ols
    -0.59
    SHIP
    -0.59
    olk
    -0.58
     flipping
    -0.57
    POSITIVE LOGITS
    4
    1.04
    3
    1.02
     3
    0.85
     4
    0.84
    Reviewed
    0.76
    Fourth
    0.72
    ileaks
    0.72
    udeau
    0.70
    awi
    0.69
    2
    0.69
    Activations Density 0.119%

    No Known Activations