Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9698
    Prev
    Next
    INDEX
    Explanations

    references to urban-related terms and names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Urban" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.83
    iris
    -0.78
    utations
    -0.76
    UNE
    -0.76
    UTERS
    -0.76
    BILITIES
    -0.74
    sembly
    -0.74
    âķIJâķIJ
    -0.72
    utes
    -0.71
    aird
    -0.70
    POSITIVE LOGITS
     Decay
    0.88
     Dictionary
    0.88
     Meyer
    0.80
    idad
    0.79
    ization
    0.77
    ized
    0.76
    icity
    0.74
     Crime
    0.74
    izable
    0.72
    ITY
    0.72
    Activations Density 0.010%

    No Known Activations