© 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. 24071
    Prev
    Next
    INDEX
    Explanations

    mentions of human beings

    oai_token-act-pair · gpt-3.5-turbo

    references to "human beings" in various contexts

    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
    etta
    -0.69
     Kitchen
    -0.66
    ORY
    -0.64
    CL
    -0.62
    Pop
    -0.61
    BALL
    -0.61
     Gillespie
    -0.61
     Soda
    -0.61
     Kerr
    -0.60
     Ridge
    -0.60
    POSITIVE LOGITS
     beings
    1.22
    terness
    0.93
     imperson
    0.87
    ĨĴ
    0.85
     Tradable
    0.84
     unworthy
    0.83
     sentient
    0.82
     rul
    0.81
     endowed
    0.80
     mortals
    0.80
    Activations Density 0.010%

    No Known Activations