© 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. 1-RES-JB
    11. 8677
    Prev
    Next
    INDEX
    Explanations

    proper nouns or technical terms related to data storage systems

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific brand or product line

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pose
    -0.75
    ropolitan
    -0.75
     Nun
    -0.68
     ç¥ŀ
    -0.67
     Corpus
    -0.66
     quo
    -0.64
     NHS
    -0.61
    folk
    -0.60
    rail
    -0.60
    feature
    -0.59
    POSITIVE LOGITS
    OME
    0.88
    inks
    0.87
    IVERS
    0.86
    INK
    0.84
    irez
    0.83
     resil
    0.80
    IVE
    0.80
    adeon
    0.79
    ESH
    0.77
    inking
    0.76
    Activations Density 0.006%

    No Known Activations