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. 16054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating agreement or collective action

    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
     bluff
    -0.64
     consolidation
    -0.61
     flats
    -0.58
     playback
    -0.58
     Survivors
    -0.58
     compression
    -0.58
     Virus
    -0.58
     Transformation
    -0.57
    elsen
    -0.57
    sterdam
    -0.57
    POSITIVE LOGITS
    Ïī
    0.78
     sidx
    0.75
    itten
    0.71
    speaking
    0.71
    apon
    0.67
    enged
    0.67
    enge
    0.65
    agher
    0.65
    interested
    0.64
    achable
    0.64
    Activations Density 0.365%

    No Known Activations