INDEX

Explanations

concepts related to identification and universal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Hentet

-0.62

forChild

-0.53

IUrlHelper

-0.52

krieg

-0.48

ytä

-0.48

saf

-0.48

 quyết

-0.48

 llaman

-0.47

رشف

-0.45

ozof

-0.45

POSITIVE LOGITS

 relatable

0.81

 empathi

0.74

 sympathize

0.73

 TextAppearance

0.73

 sympathetic

0.67

ArgsConstructor

0.67

 sympathi

0.67

 vécu

0.66

 sympathy

0.65

 vivió

0.64

Activations Density 0.171%

concepts related to identification and universal experiences

No Comments

No Known Activations