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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 2142
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    the use of the verb "had" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĺħ
    -0.60
    etter
    -0.57
    Soc
    -0.56
    States
    -0.56
    poses
    -0.56
    ethy
    -0.56
     holiest
    -0.56
    lig
    -0.54
     salute
    -0.54
     /**
    -0.54
    POSITIVE LOGITS
     undergone
    0.96
    drawn
    0.88
     dealings
    0.85
     been
    0.83
     difficulty
    0.82
    iths
    0.80
     gotten
    0.80
     trouble
    0.80
    ĸļ
    0.78
    ewitness
    0.77
    Activations Density 0.040%

    No Known Activations