INDEX

Explanations

phrases indicating availability or capacity for more requests or items

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

 تانيه

-0.95

Efq

-0.91

GEBURTSDATUM

-0.90

 Monfieur

-0.88

 cherchés

-0.83

 fevere

-0.81

</thead>

-0.80

aarrggbb

-0.80

BeginContext

-0.79

 purpoſe

-0.78

POSITIVE LOGITS

 space

1.36

 Space

1.17

Space

1.11

 SPACE

1.07

 espaço

1.05

 espacio

1.05

space

1.05

 spazio

1.04

 spaces

0.92

 room

0.92

Activations Density 0.120%

phrases indicating availability or capacity for more requests or items

No Comments

No Known Activations