INDEX

Explanations

occurrences of the beginning of code structures or programming functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ConstraintMaker

-1.01

elemField

-1.01

 мәкал

-1.01

 betweenstory

-0.97

 nakalista

-0.90

complexContent

-0.87

bitField

-0.79

StoryboardSegue

-0.79

 odkazy

-0.79

protoimpl

-0.78

POSITIVE LOGITS

0.59

↵↵↵↵

0.53

↵↵↵

0.51

 original

0.49

 ampli

0.48

 Plus

0.48

↵↵↵↵↵↵

0.47

PYX

0.47

TAIN

0.45

↵

0.45

Activations Density 0.213%

occurrences of the beginning of code structures or programming functions

No Comments

No Known Activations