© 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. 24134
    Prev
    Next
    INDEX
    Explanations

    academic disciplines or fields of study

    oai_token-act-pair · gpt-3.5-turbo

    references to educational programs or institutions

    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
    phabet
    -0.79
    ardless
    -0.79
    ãģĤ
    -0.75
    TL
    -0.66
     speedy
    -0.64
    unal
    -0.62
    gettable
    -0.61
     neutrality
    -0.60
     sequest
    -0.59
    given
    -0.59
    POSITIVE LOGITS
     Studies
    1.26
     Interpret
    0.99
     Scholars
    0.91
    udo
    0.89
     studies
    0.88
     Digest
    0.87
     Advisor
    0.87
    Studies
    0.85
    atures
    0.84
     Journals
    0.84
    Activations Density 0.009%

    No Known Activations