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. 10-RES-JB
    6. 9776
    Prev
    Next
    INDEX
    Explanations

    words related to processes or products of desalination

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of damage or degradation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parish
    -0.71
     Baptist
    -0.69
     Pupp
    -0.64
    naires
    -0.63
     Shack
    -0.63
     Hurt
    -0.63
     Counsel
    -0.62
     Pirate
    -0.62
     ANGEL
    -0.61
     accord
    -0.61
    POSITIVE LOGITS
    culated
    1.53
    cul
    1.25
    tering
    1.20
    culation
    1.17
    tered
    1.17
    med
    1.07
    ming
    1.02
    uminum
    0.99
    oric
    0.98
    culus
    0.98
    Activations Density 0.076%

    No Known Activations