© 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. 2-RES-JB
    11. 24029
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives indicating extreme degrees, such as "most," "greatest," or "highest."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being the "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.79
    itan
    -0.70
    alid
    -0.66
    rish
    -0.64
    arter
    -0.63
    pton
    -0.60
    chrom
    -0.59
    icer
    -0.59
    icter
    -0.58
     tremend
    -0.58
    POSITIVE LOGITS
    likely
    0.99
    most
    0.93
    tenance
    0.92
     Helpful
    0.82
    etheless
    0.81
    quartered
    0.77
    egu
    0.75
    popular
    0.72
     Likely
    0.72
    bidden
    0.72
    Activations Density 0.008%

    No Known Activations