INDEX

Explanations

expressions of surprise or irony in narratives

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

koľvek

-0.53

Addo

-0.46

rrggbb

-0.44

 setw

-0.42

añ

-0.41

 Generals

-0.41

ктей

-0.41

肯定是

-0.41

 bArr

-0.40

General

-0.39

POSITIVE LOGITS

 oddly

0.96

]--;

0.94

 strangely

0.93

 ironically

0.93

contentLoaded

0.89

Surprisingly

0.86

 weirdly

0.84

 surprisingly

0.83

 parado

0.81

竟

0.81

Activations Density 0.237%

expressions of surprise or irony in narratives

No Comments

No Known Activations