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. 7-RES-JB
    6. 1081
    Prev
    Next
    INDEX
    Explanations

    phosphorylated compounds and related terms

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and elements, particularly those related to phosphorus and sulfide

    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
    HEAD
    -0.89
     Mysteries
    -0.70
     Yankee
    -0.69
    Dri
    -0.66
     Cust
    -0.66
     Pupp
    -0.65
    LI
    -0.64
    backer
    -0.63
     Sisters
    -0.63
     Manager
    -0.63
    POSITIVE LOGITS
    oric
    1.22
    orescent
    1.14
    orous
    1.09
    agen
    1.08
    orus
    1.07
    atile
    1.07
    orescence
    1.06
    omen
    1.01
    oral
    1.01
    orem
    0.97
    Activations Density 0.060%

    No Known Activations