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. 9793
    Prev
    Next
    INDEX
    Explanations

    phrases starting with a colon

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct quotations or statements made by individuals

    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
     grease
    -0.70
     hemor
    -0.68
    ADS
    -0.65
     troubles
    -0.65
     trouble
    -0.63
     delinquent
    -0.62
     credits
    -0.61
     giveaway
    -0.59
     swaps
    -0.59
     contiguous
    -0.59
    POSITIVE LOGITS
     "â̦
    1.38
     "[
    1.25
     "...
    1.24
     "'
    1.24
     '[
    1.15
     "@
    1.12
     "(
    1.12
     ""
    1.09
     ".
    1.05
     "$
    1.01
    Activations Density 0.080%

    No Known Activations