INDEX

Explanations

phrases related to user interaction in a gamified context

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

Follows a string or bracket

np_acts-logits-general · gemini-2.0-flash

string literal keys

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

InitVars

-0.90

mybatisplus

-0.81

✭✭

-0.72

archiviato

-0.72

InSection

-0.69

 <=",

-0.68

WebVitals

-0.67

 سكانية

-0.66

 <>",

-0.66

LookAnd

-0.65

POSITIVE LOGITS

source

1.06

Source

0.71

 source

0.68

allclose

0.61

_('

0.60

 Reſ

0.58

soft

0.57

 Source

0.57

 Conſ

0.57

SOURCE

0.56

Activations Density 0.020%

phrases related to user interaction in a gamified context

Follows a string or bracket

string literal keys

No Comments

No Known Activations