© 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. 7-RES-JB
    11. 16748
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and control

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.72
     RAD
    -0.71
     Gleaming
    -0.68
     Sandwich
    -0.65
     cyan
    -0.63
     assemb
    -0.62
     colonial
    -0.61
     shack
    -0.61
    代
    -0.61
     guiActiveUn
    -0.60
    POSITIVE LOGITS
    £
    0.98
    Ĵ
    0.93
    ı
    0.89
    Ķ
    0.87
    lege
    0.85
    ĵ
    0.84
    uve
    0.82
    ij
    0.80
    been
    0.79
    «
    0.79
    Activations Density 0.046%

    No Known Activations