INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 greateſt

-1.03

 myſelf

-0.97

Yud

-0.96

 leaſt

-0.92

IsContent

-0.91

 ſtate

-0.91

()]

-0.91

 ſever

-0.89

 Greenland

-0.89

Rhestr

-0.88

POSITIVE LOGITS

 springfox

0.85

 للا

0.76

Viz

0.72

Ish

0.69

FormTagHelper

0.66

prägt

0.66

ionato

0.65

Iz

0.65

Daz

0.64

Mia

0.64

Activations Density 0.780%

proper nouns, particularly names and titles

No Comments

No Known Activations