INDEX

Explanations

code-related keywords that indicate control flow and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Nani

-0.67

 jezik

-0.61

 affari

-0.59

DBG

-0.59

ûr

-0.58

ighborhood

-0.58

ésus

-0.58

 Hadid

-0.58

HRC

-0.57

ViewInit

-0.57

POSITIVE LOGITS

 TestBed

0.69

 ***!

0.68

mce

0.61

RTLD

0.60

WriteBarrier

0.60

دانشنامهٔ

0.59

 chi̍t

0.59

 estimés

0.58

Искәрмәләр

0.58

 BoxFit

0.58

Activations Density 0.035%

code-related keywords that indicate control flow and error handling

No Comments

No Known Activations