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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 10657
    Prev
    Next
    INDEX
    Explanations

    words related to prestigious institutions, medical conditions, and geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    suffixes that indicate a place or institution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -1.05
    BILITY
    -0.77
    vironment
    -0.73
     sugg
    -0.67
    Cola
    -0.65
    FontSize
    -0.64
     fluorescent
    -0.61
    eers
    -0.60
     prosecut
    -0.58
    SpaceEngineers
    -0.58
    POSITIVE LOGITS
    opoulos
    0.81
    ashtra
    0.76
    bos
    0.71
    arb
    0.70
    ueller
    0.69
    oulos
    0.68
    phia
    0.67
    sein
    0.66
    nir
    0.66
    oppers
    0.66
    Activations Density 0.176%

    No Known Activations