INDEX

Explanations

code-related terminology and conditions involving null checks and logical operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

fromnode

-0.50

Du

-0.42

 APPRO

-0.42

Przypisy

-0.42

 Former

-0.41

褥

-0.40

Ra

-0.40

dup

-0.40

↵↵

-0.40

Distinctions

-0.40

POSITIVE LOGITS

 propOrder

0.74

Personendaten

0.71

HostException

0.69

RectangleBorder

0.69

ScopeManager

0.67

AnchorStyles

0.66

URLException

0.65

évaluateur

0.65

Portály

0.65

ThroughAttribute

0.65

Activations Density 0.759%

code-related terminology and conditions involving null checks and logical operations

No Comments

No Known Activations