INDEX

Explanations

references to figures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 EconPapers

-0.65

matchCondition

-0.64

曖昧さ回避

-0.63

DebuggerNonUser

-0.61

 متعلقه

-0.60

ernalia

-0.57

Искәрмәләр

-0.55

 disambiguazione

-0.54

 opér

-0.54

原始内容存档于

-0.53

POSITIVE LOGITS

 skating

0.68

 skater

0.62

 captions

0.60

 skaters

0.59

 legends

0.58

head

0.58

 prominently

0.57

figsize

0.56

 Skating

0.54

 caption

0.54

Activations Density 0.364%

references to figures in the text

No Comments

No Known Activations