© 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. 7-RES-JB
    11. 8729
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives ending in 'er'

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the suffix "er" indicating a comparative or agentive form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HF
    -0.65
    Ward
    -0.64
    RF
    -0.64
    WAR
    -0.64
    pta
    -0.62
     Pearce
    -0.62
    EP
    -0.60
     WATCHED
    -0.60
    ILLE
    -0.59
    SEA
    -0.59
    POSITIVE LOGITS
     than
    1.44
    than
    1.36
     Than
    1.35
    iating
    0.88
    atures
    0.76
     versions
    0.75
     ado
    0.73
    gow
    0.72
     tendencies
    0.70
    jack
    0.69
    Activations Density 0.054%

    No Known Activations