© 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. 0-RES-JB
    11. 1279
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or characters being alive or surviving

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being alive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inge
    -0.65
     Deter
    -0.63
     Dim
    -0.61
    xi
    -0.61
    andise
    -0.59
     Regulatory
    -0.58
     Reasons
    -0.58
     Domestic
    -0.58
     Quantity
    -0.55
    ham
    -0.55
    POSITIVE LOGITS
     alive
    4.14
     Alive
    2.69
     awake
    1.48
     intact
    1.42
     afloat
    1.40
     survives
    1.25
     dead
    1.20
     survived
    1.16
     DEAD
    1.11
    dead
    1.05
    Activations Density 0.028%

    No Known Activations