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. 0-RES-JB
    6. 7505
    Prev
    Next
    INDEX
    Explanations

    phrases related to concepts or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ory" or related terms

    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
     mornings
    -0.65
     ali
    -0.63
     cro
    -0.60
     alum
    -0.59
     Ens
    -0.59
     decl
    -0.58
     centered
    -0.57
     kilomet
    -0.57
     clean
    -0.56
     manually
    -0.56
    POSITIVE LOGITS
    ory
    4.95
    ories
    3.13
    ORY
    2.86
    orie
    2.02
    orical
    1.81
    oire
    1.66
    orial
    1.62
    oret
    1.52
    oric
    1.44
    orically
    1.37
    Activations Density 0.009%

    No Known Activations