INDEX

Explanations

beginning and headers of textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.53

-0.46

-0.45

pem

-0.44

qu

-0.42

ph

-0.42

-0.41

vu

-0.41

POSITIVE LOGITS

 myſelf

1.30

 themſelves

1.25

 Monfieur

1.23

 itſelf

1.22

 himſelf

1.21

 purpoſe

1.11

 becauſe

1.07

 ſever

1.04

 pleaſure

1.03

 iſt

1.00

Activations Density 0.347%

beginning and headers of textual content

No Comments

No Known Activations