INDEX

Explanations

code-related terms and functions, particularly in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

...

-0.55

Jährige

-0.55

masing

-0.52

tschaft

-0.52

gonic

-0.51

ibouti

-0.50

del

-0.50

mbggenerated

-0.50

ništvo

-0.49

POSITIVE LOGITS

LEIA

0.86

ंदीखरीदारी

0.77

#![

0.76

tvguidetime

0.72

Ӏ

0.71

XCTAssert

0.70

ThroughAttribute

0.69

noinspection

0.68

amaño

0.64

imetsu

0.64

Activations Density 0.063%

code-related terms and functions, particularly in programming contexts

No Comments

No Known Activations