INDEX

Explanations

quoted phrases and significant remarks within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 aimez

-0.49

tető

-0.48

 facture

-0.48

 pieno

-0.47

endtime

-0.47

 nomi

-0.46

 AssemblyCompany

-0.45

 Blau

-0.45

 mystère

-0.45

خت

-0.44

POSITIVE LOGITS

 utterances

1.07

 uttered

1.07

 utterance

0.98

 sayings

0.90

 quoted

0.88

 phrases

0.86

 paraphrase

0.86

 frases

0.85

 sentences

0.85

 frase

0.85

Activations Density 0.579%

quoted phrases and significant remarks within the text

No Comments

No Known Activations