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. 15275
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating causation or location

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage in sentences

    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
    Look
    -0.36
    —"
    -0.33
    sit
    -0.33
    No
    -0.32
    sylv
    -0.32
    ese
    -0.32
    å§
    -0.32
     besides
    -0.32
    Like
    -0.32
    Attempt
    -0.32
    POSITIVE LOGITS
    geries
    0.46
     thee
    0.44
     oneself
    0.43
     Rs
    0.40
     Shutterstock
    0.40
     infinity
    0.37
     english
    0.37
     debian
    0.37
     facebook
    0.36
     graphene
    0.35
    Activations Density 1.301%

    No Known Activations