INDEX

Explanations

elements related to options and preferences in a structured context

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

 Савезне

-1.18

 كومونز

-1.12

MigrationBuilder

-1.08

تقاوى

-1.03

IsContent

-1.01

Personendaten

-1.00

dafx

-0.96

 snippetHide

-0.94

 Administrativna

-0.92

tvguidetime

-0.90

POSITIVE LOGITS

<strong>

2.50

<b>

2.27

1.88

<em>

1.52

<code>

1.46

<u>

1.43

<i>

1.35

<sub>

0.98

<sup>

0.97

<h3>

0.89

Activations Density 0.787%

elements related to options and preferences in a structured context

No Comments

No Known Activations