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. 0-RES-JB
    6. 23483
    Prev
    Next
    INDEX
    Explanations

    phrases related to significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "meaningful" and its context related to significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illon
    -0.65
     Originally
    -0.64
    iere
    -0.64
     Virus
    -0.63
    hid
    -0.63
    rea
    -0.61
    ran
    -0.59
    hoe
    -0.59
     poster
    -0.58
     Setup
    -0.58
    POSITIVE LOGITS
     meaningful
    3.40
     meaningless
    1.81
     worthwhile
    1.71
     substantive
    1.55
     measurable
    1.51
     significant
    1.48
     useful
    1.32
     fruitful
    1.31
     tangible
    1.31
     satisfying
    1.31
    Activations Density 0.020%

    No Known Activations