INDEX

Explanations

references to academic concepts and terms

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

ération

-0.71

 Aler

-0.66

 SearchView

-0.66

pya

-0.65

latego

-0.64

󠁣

-0.62

 mCurrent

-0.61

gonic

-0.61

=?,

-0.61

 IBRARY

-0.61

POSITIVE LOGITS

 industriales

0.58

httphttps

0.54

 Signalez

0.54

sizeCache

0.52

rungsseite

0.50

ⓧ

0.47

 amables

0.47

 optar

0.45

 artificiales

0.45

 cliquant

0.45

Activations Density 0.776%

references to academic concepts and terms

No Comments

No Known Activations