Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15730
    Prev
    Next
    INDEX
    Explanations

    sentences related to actions or events happening in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the phrase "has" indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eem
    -0.65
     observing
    -0.63
     Penal
    -0.62
     typing
    -0.61
     administering
    -0.60
    Interested
    -0.60
     behold
    -0.60
     performing
    -0.58
     territ
    -0.56
     Tribe
    -0.56
    POSITIVE LOGITS
     been
    1.54
    been
    1.29
     become
    1.26
     undergone
    1.18
     arisen
    1.17
     begun
    1.12
     Been
    1.09
     gotten
    1.08
     risen
    1.02
     come
    1.01
    Activations Density 0.264%

    No Known Activations