Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5725
    Prev
    Next
    INDEX
    Explanations

    words related to weather and climate conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weather and climate conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.80
    Shares
    -0.76
    CHA
    -0.73
    yright
    -0.72
    aum
    -0.71
    Pic
    -0.70
    ittal
    -0.70
    vest
    -0.70
    NSA
    -0.68
    ibli
    -0.68
    POSITIVE LOGITS
     climates
    1.15
     temperatures
    1.06
     conducive
    1.03
     humidity
    0.96
     optimum
    0.93
     conditions
    0.92
     weather
    0.90
     temperature
    0.89
     Conditions
    0.87
     winters
    0.85
    Activations Density 0.051%

    No Known Activations