© 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. 8-RES-JB
    11. 6880
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or statements initiating or causing something

    oai_token-act-pair · gpt-3.5-turbo

    the special character sequence "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.82
     hors
    -0.75
     Palest
    -0.74
     Kirin
    -0.69
     Izan
    -0.69
     Droid
    -0.64
    ozy
    -0.63
     PST
    -0.62
     scattering
    -0.61
     RAD
    -0.61
    POSITIVE LOGITS
    almost
    0.96
    £
    0.94
    could
    0.90
    perhaps
    0.90
    should
    0.89
    Pg
    0.89
    ¸
    0.88
    ¹
    0.87
    Ĭ
    0.87
    correct
    0.86
    Activations Density 0.300%

    No Known Activations