© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22646
    Prev
    Next
    INDEX
    Explanations

    mentions of words related to elephants

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants and their associated products, particularly ivory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    port
    -0.76
     Hack
    -0.76
     Weld
    -0.75
    SB
    -0.72
     Qué
    -0.72
    Sche
    -0.71
    Online
    -0.70
    Que
    -0.70
    Hack
    -0.68
    ribut
    -0.68
    POSITIVE LOGITS
     elephant
    3.73
     elephants
    3.36
     Elephant
    2.81
     gorilla
    1.92
     ivory
    1.71
    phant
    1.63
     tigers
    1.60
     eleph
    1.60
     tiger
    1.52
     camel
    1.52
    Activations Density 0.026%

    No Known Activations