INDEX

Explanations

code snippets and programming-related structures

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

"out" or related words

np_acts-logits-general · gemini-2.0-flash

in or out transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 protoimpl

-0.75

StoryboardSegue

-0.66

 للمعارف

-0.61

Personensuche

-0.60

RenderAtEndOf

-0.57

 EconPapers

-0.55

WriteBarrier

-0.54

GraphicsUnit

-0.54

 AssemblyCulture

-0.53

POSITIVE LOGITS

out

3.12

Out

2.82

out

2.79

Out

2.71

OUT

2.50

OUT

2.21

getOut

1.94

アウト

1.87

outs

1.80

 outs

1.79

Activations Density 0.059%

code snippets and programming-related structures

"out" or related words

in or out transitions

No Comments

No Known Activations