© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 10337
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical rates or occurrences of various events

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical rates associated with negative outcomes or conditions

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

    No Comments

    Negative Logits
     severed
    -0.71
    ADRA
    -0.68
    ICLE
    -0.64
     Gleaming
    -0.64
    Pub
    -0.63
    tiny
    -0.63
     disapp
    -0.62
    ISTORY
    -0.62
     SECTION
    -0.61
    ¾
    -0.60
    POSITIVE LOGITS
     (>
    0.99
    ovi
    0.89
     (<
    0.76
     variability
    0.71
     levels
    0.69
     rates
    0.67
    aroo
    0.66
     throughput
    0.66
     dur
    0.66
    than
    0.65
    Activations Density 0.211%

    No Known Activations