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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15827
    Prev
    Next
    INDEX
    Explanations

    phrases related to climate change

    oai_token-act-pair · gpt-3.5-turbo

    references to climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.86
    onym
    -0.80
    atin
    -0.77
    stra
    -0.76
    çĦ
    -0.74
    zl
    -0.74
     Zup
    -0.73
     Niet
    -0.73
    vil
    -0.72
    VP
    -0.72
    POSITIVE LOGITS
     impacts
    1.05
     mitigation
    1.02
     devastation
    0.86
     hysteria
    0.85
     engulf
    0.85
     catastrophe
    0.84
     devast
    0.84
     denial
    0.84
     endanger
    0.83
     disasters
    0.83
    Activations Density 0.029%

    No Known Activations