INDEX

Explanations

references to scripts and scripting languages, particularly JavaScript

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

"script" or "scripts"

np_acts-logits-general · gemini-2.0-flash

script and its context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

حياته

-0.87

iyle

-0.73

 {}".

-0.68

 Tompkins

-0.68

addGap

-0.66

'".

-0.65

 gorges

-0.64

{}",

-0.63

ebra

-0.63

]<<"

-0.63

POSITIVE LOGITS

 scripts

1.24

 Scripts

1.17

 Script

1.15

 script

1.15

Scripts

1.04

 SCRIPT

1.04

SCRIPT

1.02

Script

1.02

script

0.96

cript

0.95

Activations Density 0.171%

references to scripts and scripting languages, particularly JavaScript

"script" or "scripts"

script and its context

No Comments

No Known Activations