INDEX

Explanations

proper nouns, especially names of people and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mahomet

-0.84

GraphicsUnit

-0.82

 Cæsar

-0.80

 myſelf

-0.77

 Platon

-0.77

 raiſ

-0.75

 Osiris

-0.75

HomeAsUpEnabled

-0.75

 Cadiz

-0.74

 Abbé

-0.74

POSITIVE LOGITS

Tar

0.66

Bor

0.66

Del

0.65

Var

0.62

Har

0.60

Mor

0.60

McC

0.60

Er

0.60

Gor

0.59

Ton

0.58

Activations Density 5.329%

proper nouns, especially names of people and institutions

No Comments

No Known Activations