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. 4-RES-JB
    6. 17430
    Prev
    Next
    INDEX
    Explanations

    mentions of digital media and technology-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with influential entities and components in various sectors

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

    No Comments

    Negative Logits
    lys
    -0.70
    ritch
    -0.66
     poles
    -0.66
    rily
    -0.65
    inea
    -0.65
    bats
    -0.64
    warm
    -0.60
    ueless
    -0.60
     limbo
    -0.59
     kindly
    -0.59
    POSITIVE LOGITS
     (>
    0.87
     viz
    0.86
     contender
    0.75
     namely
    0.70
    atform
    0.70
     Secondary
    0.66
    \">
    0.65
    andowski
    0.65
     earners
    0.62
     tert
    0.62
    Activations Density 0.277%

    No Known Activations