INDEX

Explanations

names and citations related to research papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

<bos>

-2.24

-1.16

-1.10

’

-1.07

-0.94

",

-0.90

-0.89

',

-0.89

).

-0.89

POSITIVE LOGITS

 myſelf

1.20

 Theſe

0.99

 pleaſure

0.98

parsedMessage

0.98

ſelf

0.95

 itſelf

0.95

 becauſe

0.94

 whoſe

0.93

 EconPapers

0.93

 varandra

0.92

Activations Density 35.114%

names and citations related to research papers

No Comments

No Known Activations