© 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. 2-RES-JB
    11. 9505
    Prev
    Next
    INDEX
    Explanations

    words related to temperature control and measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to temperature and humidity conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioned
    -0.77
    roma
    -0.76
    business
    -0.75
    gd
    -0.75
    lez
    -0.74
    vous
    -0.74
    otto
    -0.73
    pletion
    -0.72
    myra
    -0.72
    zl
    -0.71
    POSITIVE LOGITS
     temperatures
    1.16
     temperature
    1.12
     fluctuations
    1.01
     gradient
    0.99
    Temperature
    0.97
     extremes
    0.96
     cooker
    0.95
     therm
    0.90
     Temperature
    0.89
    perature
    0.88
    Activations Density 0.012%

    No Known Activations