INDEX

Explanations

mathematical expressions and formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

parsedMessage

-0.71

enumi

-0.65

ThroughAttribute

-0.62

 NSCoder

-0.61

 оригіналу

-0.59

abestanden

-0.56

getDescriptor

-0.54

 defStyleAttr

-0.54

writeField

-0.53

PMailer

-0.53

POSITIVE LOGITS

¼

0.70

 halves

0.67

³/

0.66

frac

0.64

mfrac

0.64

dfrac

0.63

²/

0.63

½

0.62

 half

0.61

agues

0.60

Activations Density 1.193%

mathematical expressions and formulas

No Comments

No Known Activations