INDEX

Explanations

functions related to data conversion and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 dataSnapshot

-0.74

awtextra

-0.73

ErrorListener

-0.72

extAlignment

-0.70

Kit

-0.69

Ath

-0.68

kit

-0.67

 Kine

-0.66

Cat

-0.65

########.

-0.64

POSITIVE LOGITS

ToString

1.85

 ToString

1.18

częściej

0.78

 "..\..\

0.77

 McCulloch

0.75

 McFadden

0.74

 propOrder

0.72

fromCharCode

0.71

‰

0.71

 Edison

0.69

Activations Density 0.036%

functions related to data conversion and representation

No Comments

No Known Activations