INDEX

Explanations

references to specific actions or notable events, particularly in terms of announcements and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

CloseOperation

-0.80

########.

-0.54

UIControlState

-0.53

findpost

-0.52

 виправивши

-0.51

-0.50

abestanden

-0.49

ⓧ

-0.49

entiary

-0.49

 اطلع

-0.47

POSITIVE LOGITS

 originally

0.90

 original

0.80

 earlier

0.79

originally

0.74

 ursprünglich

0.72

original

0.71

 Originally

0.70

 originalmente

0.70

Original

0.70

 inicial

0.69

Activations Density 0.569%

references to specific actions or notable events, particularly in terms of announcements and decisions

No Comments

No Known Activations