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. 17035
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person's actions or experiences, such as activities, roles, or events they were involved in

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the pronoun "his" along with temporal references

    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
     Canaver
    -0.69
    coins
    -0.68
    onyms
    -0.65
    eers
    -0.65
    soType
    -0.63
    facts
    -0.62
    pie
    -0.62
    zyme
    -0.61
    encers
    -0.61
    daq
    -0.61
    POSITIVE LOGITS
     tenure
    1.32
     stint
    1.28
     travels
    1.21
     journey
    1.10
     lifetime
    1.05
     introductory
    1.05
     visits
    1.05
     visit
    1.05
     brief
    1.02
     journeys
    1.02
    Activations Density 0.143%

    No Known Activations