INDEX

Explanations

contact information and resources related to programs or websites

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ſche

-0.70

 Forumite

-0.68

PyExc

-0.67

 ModelExpression

-0.67

 itſelf

-0.67

 Reſ

-0.66

#+#

-0.66

NameInMap

-0.65

writeFieldEnd

-0.65

 raiſ

-0.65

POSITIVE LOGITS

at

1.83

www

1.09

0.98

 http

0.94

www

0.85

 https

0.78

 tại

0.78

http

0.77

at

0.76

Activations Density 0.178%

contact information and resources related to programs or websites

No Comments

No Known Activations