© 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. 11451
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a list of specific items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various subjects or topics that are described as "things."

    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
    bern
    -0.72
    oku
    -0.66
    Gaza
    -0.63
    iary
    -0.62
    geon
    -0.61
     hom
    -0.61
    å¸
    -0.60
    NAS
    -0.60
    FIN
    -0.58
    Finish
    -0.58
    POSITIVE LOGITS
     happening
    1.02
     happens
    0.98
     happened
    0.95
     happen
    0.93
     happ
    0.85
     transpired
    0.83
     pertaining
    0.82
     occurring
    0.81
     imaginable
    0.80
     relating
    0.72
    Activations Density 0.038%

    No Known Activations