© 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. 7056
    Prev
    Next
    INDEX
    Explanations

    uncommon or unknown words

    oai_token-act-pair · gpt-3.5-turbo

    words or prefixes indicating negation or the absence of something

    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
     Barker
    -0.72
    minster
    -0.61
     Grayson
    -0.59
     Saras
    -0.59
    opoulos
    -0.59
     Lambert
    -0.58
     Ples
    -0.58
     Damian
    -0.56
     circle
    -0.56
     david
    -0.56
    POSITIVE LOGITS
    ailability
    1.01
    akable
    1.00
    oppable
    0.99
    cedented
    0.94
    orable
    0.89
    ables
    0.80
    erving
    0.80
    emphasis
    0.80
    QL
    0.77
    ishable
    0.76
    Activations Density 0.068%

    No Known Activations