INDEX

Explanations

phrases that express judgment, accountability, and the complexities of human behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

SBATCH

-0.67

 &___

-0.61

nantes

-0.60

ength

-0.58

CCESS

-0.57

 durata

-0.56

ORIA

-0.56

 styr

-0.55

 cáp

-0.55

 strengthening

-0.55

POSITIVE LOGITS

 understandable

0.54

 Dernière

0.52

 MainAxisSize

0.52

AutoScaleMode

0.50

 blame

0.49

_));

0.46

 explanations

0.45

かわい

0.45

DockStyle

0.44

RAI

0.44

Activations Density 0.279%

phrases that express judgment, accountability, and the complexities of human behavior

No Comments

No Known Activations