INDEX

Explanations

concepts related to media and discourse in sociological contexts

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

 myſelf

-1.31

 itſelf

-1.30

 raiſ

-1.22

 ſta

-1.22

Efq

-1.17

 Jefus

-1.16

 purpoſe

-1.11

 himſelf

-1.09

 ſever

-1.08

 iſt

-1.07

POSITIVE LOGITS

sub

0.52

di

0.49

in

0.47

 духовке

0.46

que

0.46

Per

0.45

 para

0.45

 entro

0.43

Activations Density 0.559%

concepts related to media and discourse in sociological contexts

No Comments

No Known Activations