© 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. 8-RES-JB
    11. 20093
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.81
    uria
    -0.67
    sequence
    -0.63
    NetMessage
    -0.63
    olulu
    -0.63
     seism
    -0.62
     Dul
    -0.59
    isconsin
    -0.59
     [*
    -0.59
    itionally
    -0.57
    POSITIVE LOGITS
     brothers
    0.98
     bandwagon
    0.96
     family
    0.89
     Brothers
    0.84
     sisters
    0.83
    verse
    0.81
    tones
    0.80
     clan
    0.80
     household
    0.80
     saga
    0.78
    Activations Density 0.289%

    No Known Activations