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. 2154
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to societal issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classifications of various conditions, identities, and societal issues

    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
    ravings
    -0.87
    assies
    -0.82
     Rooms
    -0.79
    doms
    -0.79
    ispers
    -0.78
    xes
    -0.78
    apses
    -0.76
    votes
    -0.76
    acters
    -0.74
    flows
    -0.73
    POSITIVE LOGITS
     spokesperson
    0.87
     reminder
    0.84
    brainer
    0.83
     sleeper
    0.82
     affair
    0.81
     unto
    0.80
     contender
    0.78
     entity
    0.78
     approximation
    0.77
     continuation
    0.75
    Activations Density 0.457%

    No Known Activations