INDEX

Explanations

terms related to comfort and usability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

PathVariable

-0.90

ArrowToggle

-0.88

 فريبيس

-0.82

CodeAttribute

-0.78

ագրություններ

-0.75

zeptember

-0.73

Ket

-0.72

GenerationType

-0.72

 knex

-0.71

 ketones

-0.69

POSITIVE LOGITS

 comfortable

1.80

 comfort

1.68

 COMFORT

1.66

Comfort

1.66

Comfortable

1.62

 Comfort

1.61

 Comfortable

1.57

comfortable

1.55

comfort

1.53

 comfor

1.51

Activations Density 0.040%

terms related to comfort and usability

No Comments

No Known Activations