Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15871
    Prev
    Next
    INDEX
    Explanations

    words related to science fiction

    oai_token-act-pair · gpt-3.5-turbo

    references to science fiction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umm
    -0.99
    hens
    -0.81
    hap
    -0.77
    çĦ
    -0.76
    realDonaldTrump
    -0.72
    imen
    -0.72
    pex
    -0.72
    tics
    -0.70
    gewater
    -0.70
    enges
    -0.70
    POSITIVE LOGITS
     novels
    1.40
     fiction
    1.33
     novelist
    1.29
     novel
    1.17
     anthology
    1.17
     writer
    1.10
     thriller
    1.10
     writers
    1.09
     literary
    1.02
     tropes
    1.00
    Activations Density 0.070%

    No Known Activations