INDEX

Explanations

code-related keywords, particularly annotations and access modifiers

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

-0.80

-0.74

↵

-0.72

-0.66

↵↵

-0.64

-0.62

-0.59

↵↵↵

-0.58

-0.57

POSITIVE LOGITS

 AssemblyProduct

1.01

 iſt

0.99

protected

0.99

 Jefus

0.97

bibfield

0.95

 للاسماء

0.94

findpost

0.93

 Majefty

0.93

ſelves

0.92

PreferredItem

0.91

Activations Density 0.079%

code-related keywords, particularly annotations and access modifiers

No Comments

No Known Activations