© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7272
    Prev
    Next
    INDEX
    Explanations

    I'm sorry, neuron 4's behavior was difficult to analyze as the activations were similar across multiple segments of text

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the speaker's thoughts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.72
    20439
    -0.72
    Ts
    -0.71
    pins
    -0.70
    MENTS
    -0.70
     Tasman
    -0.64
    bats
    -0.63
    mud
    -0.63
    INGTON
    -0.61
    annels
    -0.59
    POSITIVE LOGITS
     succeed
    0.83
     ever
    0.78
     sacrific
    0.77
     fail
    0.74
     ask
    0.73
     dive
    0.70
     wanna
    0.69
     guessed
    0.69
     happen
    0.68
     weren
    0.67
    Activations Density 0.106%

    No Known Activations