INDEX

Explanations

phrases indicating a comparison or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 becauſe

-0.74

 ſtand

-0.74

HtmlAttribute

-0.73

 cauſe

-0.72

 ſche

-0.72

Còn

-0.70

 ModelExpression

-0.70

 raiſ

-0.70

 whoſe

-0.70

HandlerContext

-0.69

POSITIVE LOGITS

0.94

 giant

0.74

an

0.69

 eines

0.65

 instanceof

0.63

 glorified

0.63

 like

0.62

是个

0.62

 bona

0.61

“

0.61

Activations Density 0.267%

phrases indicating a comparison or similarity

No Comments

No Known Activations