INDEX

Explanations

words indicating new or innovative concepts and discoveries

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

-0.93

-0.84

<b>

-0.79

</b>

-0.76

-0.70

-0.69

-0.67

Today

-0.67

POSITIVE LOGITS

 NOVEL

1.12

 Novel

1.11

Datuak

1.10

日閲覧

1.08

BibitemShut

1.07

^(@)

1.07

Cordialement

1.06

savevideo

1.04

novel

1.03

Cyfeiriadau

1.03

Activations Density 0.166%

words indicating new or innovative concepts and discoveries

No Comments

No Known Activations