INDEX

Explanations

the frequency of the word "often" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 always

-0.82

 sempre

-0.81

always

-0.74

 siempre

-0.73

 всегда

-0.69

 vždy

-0.69

 toujours

-0.68

 πάντα

-0.67

ALWAYS

-0.67

sempre

-0.66

POSITIVE LOGITS

 genug

0.96

times

0.94

 times

0.94

 xuyên

0.90

 snippetHide

0.86

 Asked

0.77

 heard

0.75

 overlooked

0.75

heard

0.74

 cited

0.73

Activations Density 0.146%

the frequency of the word "often" and its variations in various contexts

No Comments

No Known Activations