INDEX

Explanations

structured and formatted data, likely related to programming or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

setVerticalGroup

-1.04



-0.87

rbrakk

-0.80

ंदीखरीदारी

-0.79

BeginInit

-0.78

ſcher

-0.77

ConstraintMaker

-0.76

majánló

-0.75

 AssemblyTitle

-0.73

 propOrder

-0.73

POSITIVE LOGITS

0.70

The

0.61

the

0.61

<td>

0.59

0.57

0.54

0.53

<b>

0.52

="

0.50

}{*}{

0.49

Activations Density 0.104%

structured and formatted data, likely related to programming or mathematical expressions

No Comments

No Known Activations