INDEX

Explanations

references to memory buffers and associated operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

····

-0.83

PreferredItem

-0.83

TagMode

-0.79

 Sted

-0.71

UNRELATED

-0.71

Personensuche

-0.70

JSONException

-0.66

✨:

-0.65

/\.

-0.65

Stem

-0.65

POSITIVE LOGITS

 buffers

1.81

 buffer

1.75

 Buffer

1.74

 Buff

1.54

buffer

1.49

 BUFFER

1.45

buffers

1.43

Buffer

1.41

Buffers

1.36

 BUFF

1.32

Activations Density 0.090%

references to memory buffers and associated operations

No Comments

No Known Activations