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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 16930
    Prev
    Next
    INDEX
    Explanations

    words related to endangered and threatened species

    oai_token-act-pair · gpt-3.5-turbo

    terms related to endangered species and their conservation status

    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
    ibur
    -0.81
    hall
    -0.79
    arist
    -0.78
    gran
    -0.75
    hr
    -0.74
    orrow
    -0.72
    icians
    -0.69
    rist
    -0.69
    room
    -0.69
    jet
    -0.68
    POSITIVE LOGITS
     Species
    1.05
     species
    0.97
     habitat
    0.91
     wildlife
    0.87
     endangered
    0.87
     endanger
    0.84
    species
    0.83
    angered
    0.80
     poaching
    0.78
     mammals
    0.78
    Activations Density 0.016%

    No Known Activations