© 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. 4-RES-JB
    11. 439
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "dream"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dairy products and creamy textures

    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
    ahon
    -0.68
     escort
    -0.67
     closest
    -0.64
    anuts
    -0.64
    phant
    -0.62
    istant
    -0.61
    NRS
    -0.60
    ques
    -0.60
    mine
    -0.60
     linger
    -0.60
    POSITIVE LOGITS
    sie
    0.96
    s
    0.96
    edIn
    0.93
    er
    0.93
    ãĤ§
    0.92
    erate
    0.91
    éĹĺ
    0.89
    ership
    0.87
    edly
    0.85
    ski
    0.79
    Activations Density 0.029%

    No Known Activations