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. 16045
    Prev
    Next
    INDEX
    Explanations

    adjectives describing intensity or strength

    oai_token-act-pair · gpt-3.5-turbo

    references to intense competition or conflict

    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
    ulhu
    -0.82
    uration
    -0.77
    eret
    -0.71
    iture
    -0.70
    annis
    -0.70
    ajor
    -0.70
    abad
    -0.69
    pty
    -0.67
    akeru
    -0.65
    äºĶ
    -0.65
    POSITIVE LOGITS
    ãĥ£
    0.98
     fierce
    0.93
    ly
    0.91
     fiercely
    0.86
     earthqu
    0.85
     battles
    0.80
     ferocious
    0.80
     streak
    0.80
     battle
    0.77
     peaks
    0.75
    Activations Density 0.023%

    No Known Activations