© 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. 11-RES-JB
    11. 22552
    Prev
    Next
    INDEX
    Explanations

    words related to cold temperature

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to coldness or cold-blooded actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -0.81
    utan
    -0.78
    cence
    -0.73
    ucha
    -0.72
    cent
    -0.71
     Mons
    -0.71
     Motorsport
    -0.70
    CENT
    -0.68
    initialized
    -0.67
    aic
    -0.66
    POSITIVE LOGITS
    blooded
    1.13
    est
    0.89
     winters
    0.89
     turkey
    0.87
     weather
    0.86
    hearted
    0.86
    water
    0.85
     sweats
    0.83
     shoulder
    0.83
     fusion
    0.82
    Activations Density 0.022%

    No Known Activations