© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    Roman numerals being used in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of artificial intelligence organizations and standards

    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
    rooms
    -0.89
    sters
    -0.87
    ster
    -0.82
    mans
    -0.82
    tops
    -0.76
    house
    -0.75
    houses
    -0.73
    oos
    -0.70
     bunny
    -0.70
     corrid
    -0.70
    POSITIVE LOGITS
    II
    1.41
    III
    1.29
    FORE
    0.85
    Lenin
    0.84
    VI
    0.83
    Ëľ
    0.82
    Vi
    0.82
    NK
    0.82
    soever
    0.82
    irit
    0.81
    Activations Density 0.011%

    No Known Activations