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. 2481
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to political and governmental institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Westminster and related political contexts

    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
    onies
    -0.86
    href
    -0.85
    ographed
    -0.84
    osphere
    -0.82
    ograp
    -0.82
    oton
    -0.82
    vana
    -0.81
    alach
    -0.80
    rahim
    -0.76
    isode
    -0.74
    POSITIVE LOGITS
     Abbey
    1.23
    minster
    1.16
     Westminster
    0.84
     Parliament
    0.83
    boro
    0.80
     Bridge
    0.80
    shire
    0.78
     Borough
    0.78
     Hall
    0.74
     Chapel
    0.73
    Activations Density 0.009%

    No Known Activations