INDEX

Explanations

phrases indicating uncertainty or partiality in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

когда

-0.42

 springfox

-0.41

 Bele

-0.41

iseite

-0.41

stay

-0.41

même

-0.40

wal

-0.39

Przypisy

-0.39

Hour

-0.39

jsdelivr

-0.39

POSITIVE LOGITS

HtmlAttribute

0.72

GEBURTSDATUM

0.71

SharedDtor

0.67

Datuak

0.66

testify

0.66

fjspx

0.65

 كومونز

0.64

ThroughAttribute

0.64

bewerken

0.64

IndentedString

0.64

Activations Density 0.562%

phrases indicating uncertainty or partiality in statements

No Comments

No Known Activations