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. 3162
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "Ċ" and end with a numerical value, possibly related to a specific encoding or formatting within the text

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or high cardinality items in text

    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
    heit
    -0.86
    boro
    -0.74
    abouts
    -0.60
    utical
    -0.59
    ython
    -0.58
    ounce
    -0.57
    rad
    -0.56
    ophy
    -0.55
     lifes
    -0.53
     equip
    -0.52
    POSITIVE LOGITS
    Likewise
    0.85
    Meanwhile
    0.82
    Furthermore
    0.82
    Nonetheless
    0.81
    Interestingly
    0.81
    However
    0.80
    PHOTOS
    0.80
    Nevertheless
    0.80
    Ironically
    0.79
    Moreover
    0.78
    Activations Density 0.629%

    No Known Activations