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. 6210
    Prev
    Next
    INDEX
    Explanations

    references to specific animal species, particularly marine and terrestrial animals

    oai_token-act-pair · gpt-3.5-turbo

    references to endangered species and their habitats

    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
    cipled
    -0.84
    =-=-=-=-
    -0.75
    advertising
    -0.75
    ettings
    -0.74
    Reply
    -0.73
    aughs
    -0.71
    Revolution
    -0.70
    ĪĴ
    -0.70
    Hardware
    -0.70
    Money
    -0.69
    POSITIVE LOGITS
     species
    1.24
     beetle
    1.07
     specimens
    1.07
     biologist
    1.06
     habitat
    1.03
     animals
    1.01
     organisms
    1.01
     biologists
    1.01
     habitats
    1.00
     hunter
    1.00
    Activations Density 0.330%

    No Known Activations