INDEX

Explanations

phrases related to product features and specifications

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

Punctuation followed by a capitalized word

np_acts-logits-general · gemini-2.0-flash

suitable and easy features

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

Tikang

-0.75

amodel

-0.67

contentLoaded

-0.61

ंदीखरीदारी

-0.60

lusconi

-0.60

DeclareMath

-0.59

__*/

-0.59

ureusement

-0.54

)++;

-0.54

viewtopic

-0.54

POSITIVE LOGITS

 suitable

0.83

suitable

0.74

 please

0.73

 easy

0.71

it

0.70

 very

0.70

 Suitable

0.67

easy

0.67

Suitable

0.66

high

0.66

Activations Density 0.054%

phrases related to product features and specifications

Punctuation followed by a capitalized word

suitable and easy features

No Comments

No Known Activations