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. 19177
    Prev
    Next
    INDEX
    Explanations

    people from specific locations and their related behaviors or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people, particularly individuals from specific states or regions

    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
    Fly
    -0.72
    parts
    -0.70
    suit
    -0.66
    okin
    -0.65
    oots
    -0.65
    ods
    -0.64
     srfAttach
    -0.64
    red
    -0.64
    ORY
    -0.63
    Redd
    -0.63
    POSITIVE LOGITS
     who
    0.91
    '
    0.85
     Anonymous
    0.82
    paces
    0.81
     residing
    0.80
    ktop
    0.79
     alike
    0.78
    abouts
    0.77
    pace
    0.76
     living
    0.76
    Activations Density 0.079%

    No Known Activations