INDEX

Explanations

structures that indicate branching or conditional logic in code

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

 مشين

-0.85

UnusedPrivate

-0.63

rungsseite

-0.60

 aught

-0.59

 endfor

-0.59

 bezeichneter

-0.58

횟

-0.58

]=>

-0.58

 canst

-0.56

 OMIT

-0.55

POSITIVE LOGITS

BeginContext

0.72

Tembelea

0.67

 CreateTagHelper

0.67

ParallelGroup

0.65

EndContext

0.62

RTSC

0.59

GOTREF

0.58

CloseOperation

0.56

opsida

0.56

onAttach

0.55

Activations Density 0.309%

structures that indicate branching or conditional logic in code

No Comments

No Known Activations