INDEX

Explanations

references to a "base" or underlying framework in various contexts

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

The token "base" followed by certain suffixes or keywords

np_acts-logits-general · gemini-2.0-flash

words starting with base

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyTitle

-0.80

__*/

-0.75

InputTagHelper

-0.71

 دیکھیے

-0.65

 Valladolid

-0.63

JSONException

-0.63

Спасылкі

-0.63

OGND

-0.62

 gynhyrchwyd

-0.61

symptoms

-0.59

POSITIVE LOGITS

 BASE

1.49

 Base

1.41

BASE

1.29

 base

1.28

base

1.25

Bases

1.22

Base

1.19

 bases

1.17

bases

1.16

 Bases

1.13

Activations Density 0.127%

references to a "base" or underlying framework in various contexts

The token "base" followed by certain suffixes or keywords

words starting with base

No Comments

No Known Activations