INDEX

Explanations

references to agreement or consensus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 незавершена

-1.22

Personendaten

-1.15

thâu

-1.07

 bezeichneter

-1.06

UserScript

-1.04

</tfoot>

-1.03

rungsseite

-1.03

 мәкал

-1.03

jmniej

-1.01

NUMX

-1.01

POSITIVE LOGITS

0.74

0.57

0.56

0.52

0.51

is

0.50

0.49

Both

0.47

Activations Density 4.738%

references to agreement or consensus

No Comments

No Known Activations