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. 9353
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "never seen" is used

    oai_token-act-pair · gpt-3.5-turbo

    expressions of experiences or situations that have never happened before

    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
    States
    -0.67
    hod
    -0.65
    Preview
    -0.62
    Pierre
    -0.62
    Rap
    -0.62
    Notes
    -0.59
    FAQ
    -0.59
    HP
    -0.59
    uctions
    -0.58
    Lic
    -0.57
    POSITIVE LOGITS
    been
    1.09
     been
    0.98
    theless
    0.96
     since
    0.88
    izens
    0.85
     undergone
    0.83
     Been
    0.82
    ĸļ
    0.82
     existed
    0.80
     ventured
    0.78
    Activations Density 0.041%

    No Known Activations