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. 10-RES-JB
    6. 3597
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical and abstract concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express logical relationships and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.83
    ometown
    -0.80
    leased
    -0.79
    incial
    -0.78
    Alert
    -0.77
    abre
    -0.76
    ricane
    -0.74
    yout
    -0.74
    intend
    -0.73
    Coach
    -0.73
    POSITIVE LOGITS
     insofar
    1.29
     causation
    1.16
     Aristotle
    1.08
     suppose
    1.07
     empirical
    1.01
     heterogeneity
    1.01
     epist
    1.01
     philosophers
    1.00
     distinctions
    0.99
     whereas
    0.98
    Activations Density 0.428%

    No Known Activations