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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10795
    Prev
    Next
    INDEX
    Explanations

    references to surrogate-related terms like 'surrogate', 'surrogacy', and 'surrogates'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surrogacy and surrogate roles in various contexts

    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
    INESS
    -0.76
    OA
    -0.76
    ulhu
    -0.67
    awar
    -0.67
    alach
    -0.67
    ique
    -0.66
    TPS
    -0.66
    olini
    -0.65
     Tornado
    -0.65
    ucc
    -0.64
    POSITIVE LOGITS
     surrog
    1.06
     surrogate
    0.94
    rers
    0.80
     Parenthood
    0.72
    riages
    0.71
    geon
    0.69
     gest
    0.68
    ãĤ§
    0.65
    riers
    0.64
     phyl
    0.64
    Activations Density 0.022%

    No Known Activations