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. 10-RES-JB
    6. 14709
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or activities related to transactions and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.78
    agara
    -0.63
     NCT
    -0.58
     Fas
    -0.56
     Sig
    -0.54
     permitting
    -0.53
     Immunity
    -0.53
    pmwiki
    -0.52
    ady
    -0.51
     Travels
    -0.51
    POSITIVE LOGITS
    enance
    0.99
     besides
    0.93
     alongside
    0.84
    uate
    0.80
     upon
    0.80
     whenever
    0.72
     therein
    0.72
    fill
    0.68
     amidst
    0.68
    folk
    0.68
    Activations Density 0.186%

    No Known Activations