INDEX

Explanations

terms related to study design and statistical analysis

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

Text sections after a heading

np_acts-logits-general · gemini-2.0-flash

sections and headings

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

 elif

-0.81

Referanser

-0.81

 unknownFields

-0.80

etheless

-0.79

 AssemblyProduct

-0.75

 AttributeSet

-0.72

hyrchwyd

-0.72

PointerException

-0.72

Portály

-0.72

mybatisplus

-0.71

POSITIVE LOGITS

There

0.84

Following

0.82

Many

0.79

 Following

0.78

 There

0.76

During

0.75

Several

0.75

The

0.73

 Several

0.72

 During

0.72

Activations Density 0.311%

terms related to study design and statistical analysis

Text sections after a heading

sections and headings

No Comments

No Known Activations