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. 3614
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions or contests

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competitive events and nominations

    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
    ileaks
    -0.76
    imaru
    -0.61
    gru
    -0.61
    irit
    -0.61
    ighed
    -0.60
     conver
    -0.59
     intersect
    -0.59
    kinson
    -0.58
     extensively
    -0.58
    chnology
    -0.58
    POSITIVE LOGITS
     throne
    1.53
     title
    1.20
     nomination
    1.19
     prize
    1.16
     coveted
    1.16
     crown
    1.14
     mantle
    1.13
     berth
    1.11
     trophy
    1.09
     supremacy
    1.09
    Activations Density 0.347%

    No Known Activations