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. 3388
    Prev
    Next
    INDEX
    Explanations

    words related to harmony and scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harmony and balance

    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
    WD
    -0.66
    uyomi
    -0.65
    quickShipAvailable
    -0.65
    ea
    -0.64
    Attempts
    -0.63
    CVE
    -0.63
     Permanent
    -0.63
     ignorance
    -0.63
    Ward
    -0.62
    FACE
    -0.59
    POSITIVE LOGITS
    ized
    1.25
    ious
    1.16
    icity
    1.11
    ised
    1.10
    iated
    1.08
    iously
    1.06
    ically
    1.05
    ization
    1.05
    ics
    1.05
    izing
    1.04
    Activations Density 0.003%

    No Known Activations