INDEX

Explanations

items represented by asterisks, likely in a programming or documentation context

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

Code or URL related formatting

np_acts-logits-general · gemini-2.0-flash

url redirect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

OGND

-0.74

AccessorTable

-0.68

 betweenstory

-0.67

 ModelExpression

-0.66

fjspx

-0.58

oneofs

-0.58

 مرئيه

-0.57

SharedCtor

-0.56

 CreateTagHelper

-0.56

NameInMap

-0.56

POSITIVE LOGITS

SequentialGroup

0.71

)++;

0.64

0.58

 Pharmaco

0.56

jerne

0.55

 photolibrary

0.54

ScreenState

0.54

Activations Density 0.038%

items represented by asterisks, likely in a programming or documentation context

Code or URL related formatting

url redirect

No Comments

No Known Activations