INDEX

Explanations

questions and requests for explanations or assistance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-0.74

Eſ

-0.72

 greateſt

-0.70

 whoſe

-0.68

 pleaſure

-0.67

 mourut

-0.66

windowFixed

-0.65

 photolibrary

-0.64

capace

-0.64

 Chriſt

-0.64

POSITIVE LOGITS

 take

1.01

 make

1.01

be

0.98

 create

0.94

 being

0.91

go

0.91

 apply

0.90

 give

0.89

 have

0.85

 improve

0.84

Activations Density 0.053%

questions and requests for explanations or assistance

No Comments

No Known Activations