© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7724
    Prev
    Next
    INDEX
    Explanations

    phrases related to adding additional information or items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Add" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PATH
    -0.69
     Maker
    -0.66
    ··
    -0.62
    Fal
    -0.59
    cdn
    -0.59
     Gibbs
    -0.58
     Shades
    -0.58
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.56
     Twin
    -0.55
     blah
    -0.55
    POSITIVE LOGITS
    endum
    1.50
    ressing
    1.42
    resses
    1.39
    ition
    1.36
    itions
    1.30
    itional
    1.27
    icts
    1.25
    icted
    1.25
    ictive
    1.21
    ressed
    1.21
    Activations Density 0.032%

    No Known Activations