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. 3-RES-JB
    6. 8075
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning or investigating

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inquiries and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Depend
    -0.76
    wikipedia
    -0.68
    nown
    -0.67
    565
    -0.63
    247
    -0.62
    Downloadha
    -0.62
    BE
    -0.61
     Split
    -0.61
     Nadu
    -0.61
     Kimber
    -0.60
    POSITIVE LOGITS
     inqu
    1.31
     inquire
    1.27
     Inqu
    1.24
    isition
    1.19
     enqu
    1.12
     probing
    1.09
    iries
    1.08
    isitions
    1.06
    iry
    1.04
     inquired
    1.04
    Activations Density 0.013%

    No Known Activations