© 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. 9-RES-JB
    11. 5218
    Prev
    Next
    INDEX
    Explanations

    the conjunction 'at a'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transcripts
    -0.70
    onis
    -0.69
     footsteps
    -0.67
     Tayyip
    -0.67
     Invaders
    -0.65
    thia
    -0.62
    ATURES
    -0.61
    ORTS
    -0.61
    docs
    -0.60
    baugh
    -0.57
    POSITIVE LOGITS
     glance
    1.26
     rate
    0.90
     checkpoint
    0.88
     disadvantage
    0.87
     distance
    0.84
     moment
    0.83
     junction
    0.80
     level
    0.78
     leisure
    0.78
     whim
    0.77
    Activations Density 0.061%

    No Known Activations