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. 19429
    Prev
    Next
    INDEX
    Explanations

    terms related to water quality and safety

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water, particularly drinking water quality and issues

    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
    eering
    -0.68
    pload
    -0.68
    ature
    -0.68
    bable
    -0.66
    ures
    -0.64
     Mock
    -0.64
    uate
    -0.62
    eki
    -0.62
     Torment
    -0.62
    roup
    -0.62
    POSITIVE LOGITS
    melon
    1.44
     fluor
    0.88
    falls
    0.86
    loo
    0.84
    mel
    0.84
    colour
    0.84
    banks
    0.82
     advis
    0.82
    borne
    0.81
     fluoride
    0.78
    Activations Density 0.029%

    No Known Activations