INDEX

Explanations

references to programming constructs that involve variable checks and data validation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

JspWriter

-0.79

 greateſt

-0.78

 مشين

-0.76

didn

-0.76

 não

-0.75

 purpoſe

-0.74

not

-0.74

nicht

-0.73

χι

-0.72

RenderAtEndOf

-0.72

POSITIVE LOGITS

nor

1.35

 anymore

1.19

nor

0.96

any

0.91

Nor

0.89

Nor

0.85

而是

0.77

any

0.72

 بلکه

0.72

 nici

0.72

Activations Density 0.052%

references to programming constructs that involve variable checks and data validation

No Comments

No Known Activations