INDEX

Explanations

phrases that involve complexities and nuances in arguments or discussions, particularly those related to responsibility and outcomes

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

"of these" or "these" plus a following word

np_acts-logits-general · gemini-2.0-flash

quantifier + these

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 resourceCulture

-0.54

TagMode

-0.54

ngdoc

-0.52

Santis

-0.51

 تانيه

-0.49

vaného

-0.48

schaft

-0.48

']>;

-0.48

 rootReducer

-0.48

("*");

-0.47

POSITIVE LOGITS

 these

4.31

these

3.67

 These

3.43

These

3.39

 THESE

3.05

これらの

2.85

这些

2.80

這些

2.77

 этих

2.60

 estos

2.51

Activations Density 2.883%

phrases that involve complexities and nuances in arguments or discussions, particularly those related to responsibility and outcomes

"of these" or "these" plus a following word

quantifier + these

No Comments

No Known Activations

phrases that involve complexities and nuances in arguments or discussions, particularly those related to responsibility and outcomes

"of these" or "these" plus a following word

quantifier + these

No Comments

No Known Activations