© 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. 9-RES-JB
    11. 21181
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating a greater quantity or frequency in various contexts

    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
    CHAT
    -0.71
    ãĤ¨
    -0.65
    PLIC
    -0.63
    ista
    -0.60
    OTA
    -0.59
    Roaming
    -0.59
    limited
    -0.58
    onomy
    -0.58
     Regional
    -0.58
    doi
    -0.58
    POSITIVE LOGITS
     usual
    1.03
     anywhere
    0.82
    ever
    0.76
     anybody
    0.76
     any
    0.73
     existed
    0.72
     ever
    0.72
    gemony
    0.71
    did
    0.71
    icides
    0.71
    Activations Density 0.103%

    No Known Activations