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. 7585
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating manner or degree of action

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or manner

    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
    aic
    -0.72
     Window
    -0.67
     consequential
    -0.66
     Gothic
    -0.65
    emetery
    -0.65
    omorphic
    -0.65
    igo
    -0.64
    artisan
    -0.62
     guiActiveUnfocused
    -0.62
    RAW
    -0.60
    POSITIVE LOGITS
     knew
    1.21
     took
    1.19
     chose
    1.14
     withdrew
    1.14
     gave
    1.12
     wore
    1.11
     went
    1.11
     flew
    1.10
     forgot
    1.09
     drove
    1.08
    Activations Density 0.333%

    No Known Activations