INDEX

Explanations

terms related to data access operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

iconque

-0.72

nodoc

-0.67

DULE

-0.65

DIRS

-0.65

 Roskov

-0.64

 OnInit

-0.63

baseline

-0.62

programme

-0.61

virons

-0.60

nerie

-0.60

POSITIVE LOGITS

Access

1.54

access

1.45

 Access

1.42

ACCESS

1.29

 ACCESS

1.15

AccessLevel

1.07

 accesses

1.00

 access

0.96

 accessToken

0.84

 アクセ

0.81

Activations Density 0.170%

terms related to data access operations

No Comments

No Known Activations