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. 1145
    Prev
    Next
    INDEX
    Explanations

    potential scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express potential outcomes or uncertainties

    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
    ogie
    -0.87
    gar
    -0.83
    ging
    -0.80
    waters
    -0.78
    artney
    -0.76
    char
    -0.75
    bey
    -0.73
    gers
    -0.73
    ulu
    -0.73
    eye
    -0.73
    POSITIVE LOGITS
    ossibility
    0.91
    llor
    0.79
     horizon
    0.78
     pron
    0.78
     possibility
    0.78
     hypot
    0.74
     validity
    0.73
     someday
    0.73
    izons
    0.72
     unnecess
    0.72
    Activations Density 0.019%

    No Known Activations