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. 12552
    Prev
    Next
    INDEX
    Explanations

    names and titles related to Middle Eastern political figures, particularly ones with the name "Abdul."

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, specifically those with variations of the name "Abdul" and "Abdel"

    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
     Wolves
    -0.78
     Collider
    -0.77
     Rivals
    -0.76
     Syndicate
    -0.71
     Echoes
    -0.68
     Leap
    -0.67
     CFR
    -0.67
     Dominion
    -0.67
    OTH
    -0.66
     Eclipse
    -0.65
    POSITIVE LOGITS
    rahim
    1.09
    manac
    0.88
    aware
    0.88
    renheit
    0.87
     Abdul
    0.85
     Rahman
    0.83
    aina
    0.82
    rah
    0.80
    le
    0.79
    lege
    0.79
    Activations Density 0.024%

    No Known Activations