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. 0-RES-JB
    6. 21872
    Prev
    Next
    INDEX
    Explanations

    phrases related to traveling by a vehicle

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "drove" and related forms of transportation

    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
     available
    -0.66
     consistent
    -0.63
     potentially
    -0.63
     dependent
    -0.60
     avail
    -0.60
     appropriate
    -0.60
     possible
    -0.60
     difficult
    -0.60
     running
    -0.59
     relevant
    -0.59
    POSITIVE LOGITS
     drove
    2.70
     flew
    2.08
     blew
    1.98
     tore
    1.89
     threw
    1.85
     ate
    1.84
     took
    1.83
     gave
    1.82
     drew
    1.82
     went
    1.82
    Activations Density 0.028%

    No Known Activations