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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8-RES-JB
    6. 17225
    Prev
    Next
    INDEX
    Explanations

    words related to important key concepts or topics, likely in a specific field like finance or sports

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the structure or organization of information

    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
     mileage
    -0.73
     ages
    -0.65
     interchange
    -0.65
     scrambling
    -0.63
     Jihad
    -0.60
     vested
    -0.60
     guessing
    -0.60
     bang
    -0.59
     tune
    -0.59
     relegation
    -0.59
    POSITIVE LOGITS
    iens
    1.15
    rian
    1.07
    aris
    1.06
    rics
    1.03
    ctions
    1.03
    xes
    1.00
    inas
    0.99
    oga
    0.98
    nel
    0.98
    ipal
    0.98
    Activations Density 0.765%

    No Known Activations