INDEX

Explanations

expressions related to authority and power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SourceChecksum

-0.76

 disponibilités

-0.59

帖最后由

-0.53

إنه

-0.53

GroupLayout

-0.52

 dabei

-0.51

SharedDtor

-0.50

Datuak

-0.50

Lon

-0.50

EClass

-0.49

POSITIVE LOGITS

WebControls

0.67

 boucles

0.59

gründet

0.58

colnshire

0.58

mazoo

0.56

 poffible

0.56

ONTO

0.55

 enten

0.54

 ejus

0.54

 reaſon

0.54

Activations Density 0.260%

expressions related to authority and power dynamics

No Comments

No Known Activations