© 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. 16880
    Prev
    Next
    INDEX
    Explanations

    references to the vehicle model "Corolla"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of specific car models and their attributes

    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
     frame
    -0.68
     Met
    -0.67
     frames
    -0.64
     inspectors
    -0.61
     complete
    -0.61
     identical
    -0.61
     construct
    -0.60
     des
    -0.60
     spect
    -0.59
     quality
    -0.59
    POSITIVE LOGITS
    olla
    4.85
    oll
    1.32
    oller
    1.22
    allo
    1.17
    zona
    1.16
    oola
    1.03
    ulo
    0.99
    olls
    0.98
    asta
    0.98
    ulla
    0.96
    Activations Density 0.012%

    No Known Activations