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. 12-RES-JB
    6. 17734
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    actions and their evaluations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.69
     Flood
    -0.66
     CoC
    -0.66
    ij士
    -0.65
    Rank
    -0.64
    ©¶æ¥µ
    -0.63
    furt
    -0.63
     millenn
    -0.63
    Myth
    -0.63
    §
    -0.61
    POSITIVE LOGITS
    pez
    1.31
     differently
    1.13
     wrong
    1.07
     administr
    1.06
    omsday
    0.86
     professionally
    0.86
    wrong
    0.86
    vernment
    0.84
     poorly
    0.82
    hing
    0.82
    Activations Density 0.086%

    No Known Activations