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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18325
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desires and intentions related to achieving specific goals

    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
     Cosponsors
    -0.71
    BuyableInstoreAndOnline
    -0.69
    joy
    -0.66
    DragonMagazine
    -0.63
     Mens
    -0.61
    ared
    -0.60
     misled
    -0.60
    ARCH
    -0.60
    umerable
    -0.59
    afety
    -0.59
    POSITIVE LOGITS
     accomplish
    1.47
     achieve
    1.32
     happen
    1.17
     emulate
    1.10
     pursue
    1.06
     do
    1.03
     avoid
    1.00
     hear
    0.98
     see
    0.97
     discuss
    0.96
    Activations Density 0.090%

    No Known Activations