INDEX

Explanations

terms related to proposed amendments or changes in plans

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

jstor

-0.59

ьаж

-0.58

afficheront

-0.53

歹

-0.53

 createContext

-0.52

 disambiguazione

-0.52

nestjs

-0.51

 ventricle

-0.50

 pihaknya

-0.50

Решение

-0.49

POSITIVE LOGITS

 proposed

2.02

Proposed

1.89

proposed

1.85

 Proposed

1.84

 PROPOSED

1.75

 Suggested

1.58

PROPOSED

1.57

 planned

1.54

 alleged

1.54

Suggested

1.53

Activations Density 0.180%

terms related to proposed amendments or changes in plans

No Comments

No Known Activations