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. 8-RES-JB
    6. 6057
    Prev
    Next
    INDEX
    Explanations

    instances where the word "same" is used in the text

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "same" and its variations in references to past events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    runners
    -0.82
     Pwr
    -0.75
    Zip
    -0.68
     Lauder
    -0.66
    masters
    -0.66
    ujah
    -0.65
    lees
    -0.65
    icons
    -0.65
    osaurs
    -0.65
    parents
    -0.65
    POSITIVE LOGITS
     foray
    0.93
     avenue
    0.90
     article
    0.89
     vein
    0.87
     feat
    0.87
     milestone
    0.85
     predicament
    0.84
     piece
    0.84
     hurdle
    0.82
     scenario
    0.82
    Activations Density 0.091%

    No Known Activations