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. 22934
    Prev
    Next
    INDEX
    Explanations

    words related to speculation and uncertain claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spec" and its variants, suggesting a focus on speculation and conjecture

    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
    etheless
    -0.80
    jiang
    -0.71
    warm
    -0.69
     Holding
    -0.67
    ¿½
    -0.64
     standby
    -0.64
     destro
    -0.62
     Hearts
    -0.60
     Cruel
    -0.60
     disarm
    -0.59
    POSITIVE LOGITS
    ulations
    1.12
    ifications
    1.11
    ifiers
    1.04
    imen
    1.04
    imens
    1.03
    ulators
    0.96
    ript
    0.96
    ifiable
    0.94
    iper
    0.92
    ete
    0.91
    Activations Density 0.019%

    No Known Activations