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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 16000
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a location or object

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    payers
    -0.75
    mania
    -0.75
    brate
    -0.74
    JUST
    -0.71
    olicy
    -0.71
    ulet
    -0.70
    blem
    -0.64
    NES
    -0.64
    APH
    -0.63
    ï¸ı
    -0.63
    POSITIVE LOGITS
     hallway
    1.42
     doorway
    1.29
     midst
    1.27
     lobby
    1.24
     courtyard
    1.23
     driveway
    1.20
     middle
    1.20
     bathroom
    1.17
     bushes
    1.13
     woods
    1.13
    Activations Density 0.144%

    No Known Activations