© 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. 3-RES-JB
    11. 8698
    Prev
    Next
    INDEX
    Explanations

    phrases related to gradual or incremental change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gradual processes or incremental changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILLE
    -0.86
    yer
    -0.82
    ORE
    -0.77
    aucus
    -0.76
    DN
    -0.70
    REL
    -0.70
    mbuds
    -0.70
    hung
    -0.69
    gdala
    -0.69
     SPORTS
    -0.68
    POSITIVE LOGITS
     abandonment
    0.95
     progression
    0.90
     gradual
    0.90
     gratification
    0.84
     erosion
    0.82
     attrition
    0.82
     succession
    0.82
     incremental
    0.81
     descent
    0.80
    aneous
    0.78
    Activations Density 0.021%

    No Known Activations