INDEX

Explanations

phrases and words related to events and their participants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 незавершена

-1.03

تقاوى

-0.94

 initComponents

-0.84

 Paglinawan

-0.83

IsContent

-0.82

*/;

-0.82

цездатний

-0.79

 Мексичка

-0.77

."</

-0.76

?";

-0.74

POSITIVE LOGITS

 none

1.58

none

1.15

 None

1.04

None

0.99

なんと

0.93

 właśnie

0.88

 právě

0.87

 ninguém

0.84

…

0.83

 something

0.80

Activations Density 0.257%

phrases and words related to events and their participants

No Comments

No Known Activations