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. 10-RES-JB
    6. 2625
    Prev
    Next
    INDEX
    Explanations

    people's names, specifically focusing on individuals with the last name "Merritt" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter 'r'

    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
    e
    -0.79
    eers
    -0.76
    eas
    -0.74
    eer
    -0.72
     cov
    -0.70
    eq
    -0.69
     EntityItem
    -0.61
     rise
    -0.60
    eries
    -0.60
     glor
    -0.60
    POSITIVE LOGITS
    abbit
    1.32
    anges
    1.19
    uder
    1.16
    anches
    1.14
    ussia
    1.13
    ifle
    1.12
    acing
    1.10
    assic
    1.08
    acker
    1.07
    anca
    1.06
    Activations Density 0.048%

    No Known Activations