INDEX

Explanations

HTML tags and attributes, specifically focusing on table headers and captions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 释放

-0.77

Véxase

-0.77

 Garnet

-0.74

دانشنامهٔ

-0.73

Clik

-0.73

 caminha

-0.72

ViewFeatures

-0.72

 Gries

-0.71

IonicModule

-0.70

 namelijk

-0.70

POSITIVE LOGITS

<th>

3.11

、【

0.78

 (“

0.75

、“

0.71

(“

0.70

("/{

0.70

<caption>

0.70

{\"

0.68

 Schwe

0.68

thanes

0.68

Activations Density 0.047%

HTML tags and attributes, specifically focusing on table headers and captions

No Comments

No Known Activations