INDEX

Explanations

programming logic, particularly conditional statements and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ffekt

-0.57

 apply

-0.54

 للمعارف

-0.52

<bos>

-0.50

apply

-0.50

kamer

-0.47

Smallest

-0.46

 applies

-0.44

cVar

-0.44

منبع

-0.44

POSITIVE LOGITS

 propOrder

0.85

 resourceCulture

0.81

memoized

0.77

ResumeLayout

0.74

MemoryWarning

0.72

 pinulongan

0.72

 CURIAM

0.71

complexContent

0.71

 hashCode

0.69

ArgsConstructor

0.67

Activations Density 0.140%

programming logic, particularly conditional statements and data handling

No Comments

No Known Activations