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. 7690
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasoning or causation

    oai_token-act-pair · gpt-3.5-turbo

    the word "because" in various contexts

    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
    wn
    -0.79
    shaw
    -0.76
    ardon
    -0.74
    agin
    -0.73
    ns
    -0.72
    yan
    -0.68
    ery
    -0.67
    jet
    -0.67
    yr
    -0.66
    mint
    -0.66
    POSITIVE LOGITS
    */(
    0.78
     they
    0.73
     anecd
    0.64
     proxies
    0.64
    ecause
    0.63
     there
    0.63
     nobody
    0.62
     frankly
    0.61
     we
    0.60
     mathematic
    0.60
    Activations Density 0.068%

    No Known Activations