INDEX

Explanations

references to console logging and related debugging commands

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Code snippets with 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 @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

+#+#

-0.87

ⓧ

-0.85

Geplaatst

-0.82

MessageTagHelper

-0.82

migrationBuilder

-0.81

 mergeFrom

-0.76

="@+

-0.75

__':

-0.70

Viited

-0.69

Rüyada

-0.69

POSITIVE LOGITS

isable

0.52

log

0.46

iserie

0.44

 brute

0.44

 obfer

0.43

IOP

0.43

lage

0.42

 alamu

0.42

ivity

0.42

 dominance

0.42

Activations Density 0.070%

references to console logging and related debugging commands

Code snippets with console.log

console.log

No Known Activations