© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2572
    Prev
    Next
    INDEX
    Explanations

    mentions of DSLR cameras

    oai_token-act-pair · gpt-3.5-turbo

    mentions of DSL technology and associated terms

    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
    cies
    -1.05
     Burk
    -0.90
    ning
    -0.85
    ufact
    -0.85
    gun
    -0.84
    ting
    -0.81
    lein
    -0.80
    furt
    -0.79
    hof
    -0.79
    ugen
    -0.79
    POSITIVE LOGITS
     immersion
    0.81
    ADE
    0.81
    IFF
    0.80
    ANS
    0.80
     Crown
    0.77
    DOM
    0.77
    ORD
    0.76
    DOC
    0.75
    Applications
    0.73
    ORE
    0.72
    Activations Density 0.012%

    No Known Activations