© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    terms related to aerobic exercises and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    words related to phobias and aerobic activities

    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
    avers
    -0.70
    IRD
    -0.66
    yer
    -0.64
     telesc
    -0.63
     largeDownload
    -0.63
     Premium
    -0.62
    Money
    -0.61
    eer
    -0.60
     Gundam
    -0.59
     kernels
    -0.59
    POSITIVE LOGITS
    obic
    1.65
    obia
    1.13
    osate
    0.92
    cum
    0.86
    artment
    0.86
    oking
    0.83
    keley
    0.83
    ategory
    0.77
    stairs
    0.77
    jit
    0.76
    Activations Density 0.012%

    No Known Activations