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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 10339
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning experience or belonging in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal experiences or testimonials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    forth
    -0.74
     guiIcon
    -0.70
    nature
    -0.64
     Haram
    -0.63
     2020
    -0.63
    phabet
    -0.63
    Pg
    -0.63
    2020
    -0.63
    mere
    -0.63
     2024
    -0.63
    POSITIVE LOGITS
     experien
    1.31
     anecd
    1.20
     firsthand
    1.07
     clients
    1.04
     instances
    1.02
     myself
    1.01
     attest
    0.99
     experiences
    0.99
    romy
    0.97
     experience
    0.97
    Activations Density 0.506%

    No Known Activations