INDEX

Explanations

specific programming or configuration instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

^(@)

-0.73

Pranala

-0.72

 ſtre

-0.72

 ſever

-0.72

 houſe

-0.71

 Majefty

-0.70

 purpoſe

-0.69

 ſta

-0.68

">'.$

-0.67

-0.66

POSITIVE LOGITS

__':

0.51

dfa

0.51

ocardial

0.49

__':

0.48

 Depends

0.47

WebKit

0.47

The

0.46

Depends

0.46

HomeAsUpEnabled

0.45

getDoctrine

0.45

Activations Density 0.026%

specific programming or configuration instructions

No Comments

No Known Activations