INDEX

Explanations

references to internal and external structures or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 McClure

-0.83

OGND

-0.80

GrantedAuthority

-0.79

Pue

-0.78

 spéciaux

-0.78

 équipée

-0.78

 morire

-0.76

 revista

-0.76

SuppressMessage

-0.75

 تضيفلها

-0.74

POSITIVE LOGITS

 internal

2.13

 Internal

2.08

internal

2.02

Internal

1.99

 INTERNAL

1.83

 internally

1.66

INTERNAL

1.61

 internas

1.30

 Intern

1.29

 internals

1.27

Activations Density 0.058%

references to internal and external structures or processes

No Comments

No Known Activations