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. 4-RES-JB
    6. 19270
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" and similar terms indicating subjects or topics in context

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

    No Comments

    Negative Logits
    Gender
    -0.77
    orse
    -0.69
    hart
    -0.68
    mma
    -0.66
    pat
    -0.65
    priv
    -0.64
    tnc
    -0.64
     Aid
    -0.64
    aca
    -0.63
    grass
    -0.62
    POSITIVE LOGITS
     nonetheless
    1.38
     nevertheless
    1.34
     persisted
    0.99
     fortunately
    0.97
     still
    0.89
    theless
    0.89
     certainly
    0.89
    'll
    0.89
     couldn
    0.87
     cannot
    0.87
    Activations Density 0.359%

    No Known Activations