© 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. 10-RES-JB
    11. 11097
    Prev
    Next
    INDEX
    Explanations

    numbers in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or stipulations based on numerical changes or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.55
    aith
    -0.54
    AFP
    -0.54
    BUT
    -0.53
    rored
    -0.53
    ibliography
    -0.52
    ĺħ
    -0.50
    owship
    -0.50
    \.
    -0.49
     gobl
    -0.49
    POSITIVE LOGITS
     onwards
    1.07
     to
    1.07
     onward
    1.01
     beginnings
    0.84
    to
    0.82
     downwards
    0.76
     To
    0.73
     standpoint
    0.72
     inception
    0.71
     unto
    0.70
    Activations Density 0.282%

    No Known Activations