INDEX

Explanations

syntax elements and delimiters in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

NUMX

-1.06

UpInside

-0.78

 ་་

-0.76

⿷

-0.76

źródło

-0.76

IBLIO

-0.76

 RIPRODUZIONE

-0.74

〢

-0.73

leſs

-0.72

ſelves

-0.72

POSITIVE LOGITS

RegressionTest

0.64

for

0.60

if

0.60

0.53

0.50

free

0.47

↵

0.47

0.46

while

0.46

Expertise

0.46

Activations Density 0.793%

syntax elements and delimiters in code snippets

No Comments

No Known Activations