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. 2011
    Prev
    Next
    INDEX
    Explanations

    topics related to urban development and changes in infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social dynamics and interactions

    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
     helicop
    -0.60
    anooga
    -0.55
     outwe
    -0.52
     disadvant
    -0.52
     thereof
    -0.50
    }}
    -0.47
     behav
    -0.46
     wore
    -0.46
     slept
    -0.46
     afterward
    -0.45
    POSITIVE LOGITS
     âĢº
    0.51
    undrum
    0.44
    pmwiki
    0.44
    agonists
    0.43
    lations
    0.42
    osures
    0.42
     yet
    0.40
     lately
    0.40
     SERV
    0.39
    pots
    0.39
    Activations Density 2.436%

    No Known Activations