INDEX

Explanations

references to service quality and team dynamics in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.65

 Apparently

-0.63

 Partly

-0.63

 Exacts

-0.62

 Sometime

-0.61

MessageOf

-0.61

Apparently

-0.61

neux

-0.61

andExpect

-0.59

+#+#

-0.59

POSITIVE LOGITS

 understands

0.92

 understand

0.90

 pride

0.90

 prides

0.82

 specializes

0.82

 specialize

0.78

understand

0.76

 offer

0.75

 begrij

0.75

 specialise

0.72

Activations Density 0.102%

references to service quality and team dynamics in a professional context

No Comments

No Known Activations