INDEX

Explanations

specific terms and proper nouns related to locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-1.14

-1.00

-0.99

-0.98

-0.94

-0.93

-0.84

-0.82

ng

-0.81

ly

-0.78

POSITIVE LOGITS

posedge

0.97

 ſhe

0.95

 poffe

0.95

 raiſ

0.94

LDA

0.93

 myſelf

0.93

 Jefus

0.93

elfare

0.90

 itſelf

0.90

 photolibrary

0.89

Activations Density 0.896%

specific terms and proper nouns related to locations or entities

No Comments

No Known Activations