© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22372
    Prev
    Next
    INDEX
    Explanations

    references to locations or activities related to the beach

    oai_token-act-pair · gpt-3.5-turbo

    references to beaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Synd
    -0.76
     Companion
    -0.73
    relevant
    -0.73
     Cousins
    -0.72
    onom
    -0.71
     UID
    -0.70
    RIPT
    -0.70
    mr
    -0.69
     âĶ
    -0.68
     Minotaur
    -0.66
    POSITIVE LOGITS
     beach
    3.47
     beaches
    2.87
     Beach
    2.32
     coastline
    1.83
     shore
    1.78
     waterfront
    1.54
     coast
    1.53
     coastal
    1.46
     surf
    1.44
     ocean
    1.42
    Activations Density 0.011%

    No Known Activations