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. 12212
    Prev
    Next
    INDEX
    Explanations

    names, particularly the last name "Poroshenko."

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their associates

    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
     newsp
    -0.65
    izont
    -0.63
    liest
    -0.62
    rike
    -0.61
    fuel
    -0.60
     seeds
    -0.59
    Rev
    -0.58
     welf
    -0.58
    itudinal
    -0.57
     comprom
    -0.56
    POSITIVE LOGITS
    zyk
    0.88
    igham
    0.86
    vous
    0.84
    enegger
    0.80
    obyl
    0.77
    icz
    0.76
    Äĩ
    0.75
    oglu
    0.75
    puff
    0.74
    enei
    0.72
    Activations Density 0.044%

    No Known Activations