INDEX

Explanations

mentions of entities, particularly in the context of emotional themes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

DebuggerNonUser

-0.88

InjectMocks

-0.87

Бахар

-0.80

PerformLayout

-0.73

 Labrador

-0.69

pozorn

-0.67

GIVEREF

-0.67

存于互联网档案馆

-0.66

 fidu

-0.63

 replaceable

-0.61

POSITIVE LOGITS

 Kelly

0.78

Entity

0.73

Kelly

0.72

 Gary

0.66

 KELLY

0.64

 kelly

0.63

 upset

0.62

Gary

0.59

 McCormack

0.58

 Henry

0.56

Activations Density 0.050%

mentions of entities, particularly in the context of emotional themes

No Comments

No Known Activations