INDEX

Explanations

references to legal or geographic locations and specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

|}{}

-0.61

 فهي

-0.59

ParallelGroup

-0.58

 ***!

-0.57

EndInit

-0.52

Viitteet

-0.52

AddTagHelper

-0.52

évaluateur

-0.51

 pinulongan

-0.51

mäs

-0.50

POSITIVE LOGITS

 yesterday

0.66

 Langmuir

0.65

 earlier

0.64

 MessageBoxIcon

0.63

yesterday

0.57

knapp

0.56

 vergangenen

0.55

 near

0.55

 förra

0.55

 Tuesday

0.55

Activations Density 0.328%

references to legal or geographic locations and specific entities

No Comments

No Known Activations