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. 9-RES-JB
    6. 15981
    Prev
    Next
    INDEX
    Explanations

    adjectives describing movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    frequent punctuation or delimiters in text, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reprene
    -0.87
    itarian
    -0.85
    iless
    -0.79
    izen
    -0.76
    izoph
    -0.74
    onym
    -0.74
    ictionary
    -0.72
    ivist
    -0.70
    urat
    -0.69
    scribe
    -0.69
    POSITIVE LOGITS
     scoring
    1.19
     averaging
    1.17
     finishing
    1.11
     albeit
    1.05
    scoring
    0.98
     opting
    0.97
     hitting
    0.97
     earning
    0.97
     completing
    0.96
     totaling
    0.96
    Activations Density 0.237%

    No Known Activations