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. 23313
    Prev
    Next
    INDEX
    Explanations

    contractions of "have" and "ve"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the contraction "we've."

    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
    eem
    -0.67
    ealing
    -0.63
    Reviewer
    -0.61
    ancing
    -0.60
    UE
    -0.60
    rative
    -0.60
     Torrent
    -0.59
    Subject
    -0.59
    eller
    -0.58
    ace
    -0.57
    POSITIVE LOGITS
     gotta
    1.44
     been
    1.37
    been
    1.37
     got
    1.22
     Been
    1.18
     gotten
    1.16
     undergone
    0.93
     gone
    0.92
    hran
    0.90
    gotten
    0.89
    Activations Density 0.043%

    No Known Activations