Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 4476
    Prev
    Next
    INDEX
    Explanations

    names of political leaders and figures, particularly related to Iran

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and their authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ment
    -0.82
     Oregon
    -0.72
    horn
    -0.69
    leg
    -0.69
    mented
    -0.68
     Dover
    -0.68
     Enchant
    -0.66
     Ops
    -0.66
     Sussex
    -0.65
     Delaware
    -0.65
    POSITIVE LOGITS
    enei
    1.23
    pour
    0.98
    nis
    0.94
    ollah
    0.84
     Seym
    0.82
     dissidents
    0.81
     Kham
    0.78
    rpm
    0.76
    idium
    0.76
    xual
    0.72
    Activations Density 0.056%

    No Known Activations