INDEX

Explanations

variables related to research outcomes and findings

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

 hers

-0.51

 Schröder

-0.46

 viser

-0.45

 attacc

-0.44

 mine

-0.44

 female

-0.43

izia

-0.43

евна

-0.42

Value

-0.42

 Popov

-0.42

POSITIVE LOGITS

CloseOperation

1.04

MigrationBuilder

0.97

脚注の使い方

0.94

 ویکی‌پدیا

0.93

 صوتيه

0.93

Carriera

0.89

躇

0.86

interopRequire

0.85

sidemargin

0.85

Билгалдахарш

0.85

Activations Density 0.289%

variables related to research outcomes and findings

No Comments

No Known Activations