INDEX

Explanations

technical terms and jargon related to specific processes or fields

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

-0.74

NewUrlParser

-0.72

-0.69

-0.66

 estimés

-0.64

 }}"></

-0.63

føl

-0.63

-0.62

Me

-0.61

POSITIVE LOGITS

Efq

1.36

 Majefty

1.28

 itſelf

1.25

 Monfieur

1.23

 themſelves

1.19

 Diſ

1.18

 myſelf

1.18

 ſche

1.16

 pleaſure

1.14

 Theſe

1.14

Activations Density 0.823%

technical terms and jargon related to specific processes or fields

No Comments

No Known Activations