INDEX

Explanations

personal pronouns, particularly first-person singular references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

never

-0.62

 never

-0.60

 luôn

-0.56

 will

-0.55

always

-0.55

 always

-0.52

 также

-0.52

Never

-0.51

 gärna

-0.51

 also

-0.50

POSITIVE LOGITS

 first

0.92

 inevitably

0.80

 først

0.79

 firſt

0.77

 pertama

0.75

 finally

0.73

 firft

0.72

 <=",

0.71

IntoConstraints

0.71

 ﬁrst

0.70

Activations Density 0.241%

personal pronouns, particularly first-person singular references

No Comments

No Known Activations

personal pronouns, particularly first-person singular references

No Comments

No Known Activations