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. 3229
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by words indicating a specific situation or context

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    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
    SHIP
    -0.82
     greets
    -0.70
     reacts
    -0.65
     enjoys
    -0.65
    neys
    -0.64
     succeed
    -0.62
    gdala
    -0.61
    yles
    -0.61
     observes
    -0.59
    aces
    -0.59
    POSITIVE LOGITS
    lined
    0.91
    escap
    0.87
    versely
    0.79
    cluded
    0.77
    built
    0.76
     essence
    0.75
    herent
    0.75
    adequ
    0.75
     fact
    0.74
    accessible
    0.74
    Activations Density 0.186%

    No Known Activations