INDEX

Explanations

references to specific individuals or entities in the context of actions or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 probably

-0.72

probably

-0.70

Probably

-0.64

certainly

-0.59

 sicherlich

-0.58

 Probably

-0.56

 probabilmente

-0.54

 sicuramente

-0.54

 doubtless

-0.54

原始内容存档于

-0.53

POSITIVE LOGITS

 ever

0.89

 jemals

0.80

TestingModule

0.75

 anything

0.74

 acaso

0.72

 fizer

0.68

anything

0.66

万一

0.66

 denn

0.66

 alguno

0.66

Activations Density 0.377%

references to specific individuals or entities in the context of actions or opinions

No Comments

No Known Activations