© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    references to enhancing the well-being or productivity of a group or community

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their interactions

    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
    OPLE
    -0.62
     Precision
    -0.62
     Tucson
    -0.60
    oku
    -0.60
    neck
    -0.58
    wave
    -0.57
     Balt
    -0.56
    ller
    -0.56
     CNS
    -0.56
     magnitude
    -0.56
    POSITIVE LOGITS
     alike
    0.83
     behave
    0.79
     fail
    0.76
     appear
    0.72
     adhere
    0.72
     suffer
    0.70
     disappear
    0.70
     simultaneously
    0.69
     emulate
    0.68
     survive
    0.67
    Activations Density 0.506%

    No Known Activations