© 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. 5291
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "take a look" or variations of it are used

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "take a look."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    iHUD
    -0.72
    Cele
    -0.59
    cffff
    -0.58
    theless
    -0.57
    icc
    -0.56
    ufact
    -0.55
     fabrication
    -0.55
    RIC
    -0.54
     Methods
    -0.53
    answered
    -0.53
    POSITIVE LOGITS
    ahead
    0.90
    enary
    0.79
    ression
    0.79
    atio
    0.74
    ayson
    0.74
     towards
    0.73
     toward
    0.72
    behind
    0.71
    oscope
    0.70
    ative
    0.69
    Activations Density 0.036%

    No Known Activations