INDEX

Explanations

concepts related to existence and identity

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

abstract academic concepts

np_acts-logits-general · gemini-2.0-flash

abstract concepts and truths

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

Not in Any Lists

No Comments

Negative Logits

ніципалі

-0.71

apnews

-0.61

 ComVisible

-0.61

bbers

-0.58

ⓧ

-0.58

WillAppear

-0.56

unnitel

-0.55

HasForeignKey

-0.55

TagHelper

-0.54

RTDA

-0.54

POSITIVE LOGITS

 itself

0.73

qua

0.71

 constitutive

0.70

 constituted

0.64

 understood

0.62

 presup

0.61

qua

0.59

 operating

0.59

 instantiated

0.59

 conceived

0.58

Activations Density 0.445%

concepts related to existence and identity

abstract academic concepts

abstract concepts and truths

No Comments

No Known Activations