INDEX

Explanations

occurrences of the word "for"

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

Followed by "example" or similar words

np_acts-logits-general · gemini-2.0-flash

introducing examples

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 nakalista

-0.83

twimg

-0.75

withIdentifier

-0.68

principalColumn

-0.67

+#+#

-0.66

oa̍t

-0.66

 prossima

-0.64

 通販

-0.63

 Meksiku

-0.62

 vPvB

-0.61

POSITIVE LOGITS

 example

2.60

 instance

1.80

example

1.66

 ejemplo

1.53

 exemplo

1.47

 esempio

1.43

 eksempel

1.39

 exemple

1.35

 Beispiel

1.29

Example

1.25

Activations Density 0.130%

occurrences of the word "for"

Followed by "example" or similar words

introducing examples

No Comments

No Known Activations