INDEX

Explanations

sections of text that delve deeply into detail about specific topics or concepts

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

@"/

-0.64

IVEREF

-0.57

windowFixed

-0.55

EDEFAULT

-0.55

+#+#

-0.53

 adipis

-0.53

 发表于

-0.51

makeConstraints

-0.50

inghouse

-0.48

zések

-0.47

POSITIVE LOGITS

 detail

3.57

 details

3.40

detail

3.06

 Detail

3.04

details

2.98

 Details

2.96

 DETAIL

2.79

Details

2.77

 détail

2.76

Detail

2.76

Activations Density 0.525%

sections of text that delve deeply into detail about specific topics or concepts

No Comments

No Known Activations