INDEX

Explanations

proper nouns and specific terms related to organizations or entities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 ду

-1.92

Ду

-1.20

 Ду

-1.11

Du

-0.76

ду

-0.73

Du

-0.73

du

-0.72

DU

-0.61

Dup

-0.61

Duk

-0.60

POSITIVE LOGITS

 AppCompatTheme

0.54

 Numerade

0.53

clusal

0.45

tvguidetime

0.45

 coque

0.44

hound

0.42

Apellido

0.41

TagMode

0.41

mitos

0.41

hounds

0.41

Activations Density 0.001%

proper nouns and specific terms related to organizations or entities

No Comments

No Known Activations