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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15214
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events in a social or political context

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships and connections

    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
    SPONSORED
    -0.76
     WATCH
    -0.65
    ilater
    -0.63
    ciation
    -0.60
    aring
    -0.59
    %:
    -0.58
     respectively
    -0.58
    iott
    -0.58
    reflect
    -0.57
    Chart
    -0.57
    POSITIVE LOGITS
    utsche
    0.82
     corpse
    0.68
     dummy
    0.67
     airs
    0.67
     sofa
    0.66
    geon
    0.65
    izen
    0.64
     Dragonbound
    0.63
     phony
    0.63
     lifeless
    0.62
    Activations Density 0.963%

    No Known Activations