INDEX

Explanations

phrases related to personal identity and self-perception

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

After the word "being" or "be"

np_acts-logits-general · gemini-2.0-flash

be or being followed by a state

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

 NgModule

-0.72

 pidiendo

-0.71

 tratando

-0.70

ArgsConstructor

-0.70

DoubleQuotes

-0.68

 insisting

-0.67

 attempting

-0.67

AutoScale

-0.66

 desiring

-0.66

 GetEnumerator

-0.66

POSITIVE LOGITS

 part

0.58

 apart

0.56

iez

0.54

 đó

0.51

 yourself

0.51

 ולה

0.51

 involved

0.51

 ourselves

0.49

 kullanılır

0.49

 around

0.48

Activations Density 0.176%

phrases related to personal identity and self-perception

After the word "being" or "be"

be or being followed by a state

No Comments

No Known Activations