INDEX

Explanations

occurrences of logging statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

aronder

-0.77

 AssemblyProduct

-0.76

 Bianchi

-0.74

PerformLayout

-0.73

stateProvider

-0.72

"]="

-0.67

 InputDecoration

-0.67

tagHelperRunner

-0.66

matchCondition

-0.65

AndEndTag

-0.64

POSITIVE LOGITS

log

3.65

log

3.53

Log

3.02

Log

2.94

LOG

2.88

LOG

2.85

 logs

2.82

 Logs

2.62

logs

2.46

Slf

2.28

Activations Density 0.066%

occurrences of logging statements

No Comments

No Known Activations

occurrences of logging statements

No Comments

No Known Activations