© 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. 1-RES-JB
    11. 20131
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "advent."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "advent" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sasha
    -0.59
     Breath
    -0.58
    aves
    -0.58
    verbs
    -0.57
     veins
    -0.57
     Kubrick
    -0.56
    protein
    -0.55
    Crystal
    -0.55
    VO
    -0.53
     Biological
    -0.53
    POSITIVE LOGITS
     advent
    1.15
    itious
    0.96
    itial
    0.93
    urous
    0.86
    ãĥ¼ãĥĨãĤ£
    0.85
    reprene
    0.83
    ãĥ¼ãĥĨ
    0.82
    iat
    0.76
    uria
    0.76
    uring
    0.75
    Activations Density 0.005%

    No Known Activations