© 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. 6321
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to military or combat terminology, such as "saber" and "Fang."

    oai_token-act-pair · gpt-3.5-turbo

    references to 'saber' and other related terminology in various contexts

    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
     McA
    -0.96
    oke
    -0.81
    uters
    -0.74
     Dover
    -0.73
    icut
    -0.72
    essa
    -0.72
     Airlines
    -0.70
    ipop
    -0.69
     Pharma
    -0.68
     Osc
    -0.67
    POSITIVE LOGITS
     sab
    0.89
    ystem
    0.84
     guiActiveUn
    0.81
    lasses
    0.79
    emen
    0.78
    raph
    0.77
    ses
    0.76
    xual
    0.76
     glim
    0.73
    pread
    0.71
    Activations Density 0.019%

    No Known Activations