INDEX

Explanations

instances of console logging statements in programming contexts

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

Text including "console.log"

np_acts-logits-general · gemini-2.0-flash

console.log

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

+#+#

-0.87

__':

-0.82

 EconPapers

-0.80

Tikang

-0.75

Tembelea

-0.74

 acceptez

-0.71

kháu

-0.71

StoryboardSegue

-0.69

ⓧ

-0.69

 resourceCulture

-0.67

POSITIVE LOGITS

log

0.89

log

0.88

 logs

0.65

 logging

0.65

Log

0.62

Log

0.61

 Overhead

0.58

LOG

0.58

getLog

0.54

LOGGER

0.53

Activations Density 0.011%

instances of console logging statements in programming contexts

Text including "console.log"

console.log

No Comments

No Known Activations