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. 2-RES-JB
    6. 2914
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of meaning or significance

    oai_token-act-pair · gpt-3.5-turbo

    terms that express a lack of significance or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.81
    asio
    -0.73
    orthy
    -0.73
    oin
    -0.72
    ocker
    -0.71
    ept
    -0.69
    emis
    -0.68
    raviolet
    -0.67
    aeper
    -0.67
    aws
    -0.66
    POSITIVE LOGITS
     meaningless
    0.96
     pointless
    0.88
     nonsense
    0.84
     waste
    0.83
     useless
    0.79
     wastes
    0.79
     aside
    0.79
     irrelevant
    0.76
     kidding
    0.75
     idiots
    0.74
    Activations Density 0.025%

    No Known Activations