INDEX

Explanations

terms related to roles and tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

DebuggerStep

-0.69

 gainera

-0.59

Amicalement

-0.53

 Roskov

-0.52

eriksaan

-0.52

 capital

-0.51

رشف

-0.51

Chham

-0.50

windowFixed

-0.50

 Suivez

-0.50

POSITIVE LOGITS

hash

0.74

mybatisplus

0.74

Hash

0.72

complexType

0.71

xaml

0.70

StoryboardSegue

0.68

 hack

0.67

 hash

0.65

SuspendLayout

0.64

 IndexPath

0.63

Activations Density 1.623%

terms related to roles and tasks

No Comments

No Known Activations