Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8544
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions or directives

    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
     upheld
    -0.76
     sustained
    -0.75
     valued
    -0.75
     sustainability
    -0.70
     affirmed
    -0.70
    anty
    -0.69
     enriched
    -0.69
     neighb
    -0.69
     benefited
    -0.68
     teased
    -0.68
    POSITIVE LOGITS
    Setup
    1.24
    Create
    1.23
    STEP
    1.22
    Step
    1.21
    Install
    1.18
    Remove
    1.15
    METHOD
    1.12
    Method
    1.08
    Start
    1.06
    Apply
    1.05
    Activations Density 0.284%

    No Known Activations