INDEX

Explanations

instances of the word "what" in various contexts, often indicating uncertainty or inquiry

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shadowOpacity

-0.69

XmlEnum

-0.69

 InputDecoration

-0.69

 MainAxisSize

-0.66

 contextLoads

-0.65

#%

-0.65

gebra

-0.64

Efq

-0.64

nachron

-0.61

 Vikipedi

-0.61

POSITIVE LOGITS

 what

0.66

how

0.61

чя

0.54

 Derfor

0.54

proto

0.54

descriptor

0.53

AFX

0.53

 للمعارف

0.53

￣)

0.52

webElementXpaths

0.50

Activations Density 0.074%

instances of the word "what" in various contexts, often indicating uncertainty or inquiry

No Comments

No Known Activations