INDEX

Explanations

expressions indicating successful functioning or performance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ExecuteAsync

-0.75

bootstrapcdn

-0.74

ScopeManager

-0.71

RenderAtEndOf

-0.68

PhysRevD

-0.64

URLException

-0.64

<>("

-0.64

AndEndTag

-0.62

 Normdatei

-0.61

IntoConstraints

-0.61

POSITIVE LOGITS

 well

0.86

 fine

0.84

 better

0.84

 perfectly

0.78

better

0.69

 best

0.67

ok

0.66

 flawlessly

0.65

 wonders

0.65

 properly

0.64

Activations Density 0.135%

expressions indicating successful functioning or performance

No Comments

No Known Activations