INDEX

Explanations

occurrences of the word "Taken."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

setViewName

-0.78

warnai

-0.74

 gioia

-0.73

 stället

-0.73

AddWithValue

-0.73

 Parcelable

-0.72

 Gegenteil

-0.71

 antaranya

-0.71

 urgencia

-0.69

 felicità

-0.68

POSITIVE LOGITS

eken

0.98

 Fallen

0.89

 grown

0.88

 flown

0.87

Drawn

0.87

 Kuan

0.86

ization

0.85

>`

0.83

 Bona

0.83

 spoken

0.81

Activations Density 0.035%

occurrences of the word "Taken."

No Comments

No Known Activations