INDEX

Explanations

programming and coding constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AndEndTag

-0.67

apunov

-0.65

帖最后由

-0.60

 Waray

-0.59

 betweenstory

-0.59

RTEX

-0.58

Dwarf

-0.58

󠁢

-0.57

ospels

-0.56

 ThemeData

-0.56

POSITIVE LOGITS

 الحره

0.58

↵

0.58

TagMode

0.56

redirected

0.54

разу

0.54

chra

0.51

öö

0.50

 taas

0.49

↵↵↵

0.49

Activations Density 0.086%

programming and coding constructs

No Comments

No Known Activations