© 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. 9-RES-JB
    6. 1814
    Prev
    Next
    INDEX
    Explanations

    phrases related to similarities or comparisons between different entities

    oai_token-act-pair · gpt-3.5-turbo

    concepts of similarity and comparison

    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
    unin
    -0.63
     extraord
    -0.61
    chieve
    -0.60
     optional
    -0.59
    overe
    -0.56
     nascent
    -0.55
     bystand
    -0.55
    Emer
    -0.54
    ischer
    -0.54
    optional
    -0.53
    POSITIVE LOGITS
    same
    0.85
     twice
    0.77
     as
    0.71
     applies
    0.65
     principals
    0.63
    ait
    0.61
    natureconservancy
    0.59
    azon
    0.59
    nings
    0.58
    inson
    0.58
    Activations Density 0.142%

    No Known Activations