INDEX

Explanations

numbers and their associated values or components

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

gim

-0.65

 nahilalakip

-0.64

Sparta

-0.63

scrollPane

-0.60

orothy

-0.60

 Merrill

-0.59

multer

-0.58

 transfieras

-0.58

pruch

-0.57

 Sarkar

-0.57

POSITIVE LOGITS

UNRELATED

0.96

 jakarta

0.81

AndEndTag

0.78

 SafeMath

0.77

JSONException

0.77

 kaynağından

0.72

 JLabel

0.71

 enfans

0.70

TagMode

0.69

 foncé

0.69

Activations Density 0.304%

numbers and their associated values or components

No Comments

No Known Activations