INDEX

Explanations

terms related to annoyance or frustrating experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

LookAnd

-0.77

 AssemblyCulture

-0.71

 مشين

-0.68

 despair

-0.60

rrggbb

-0.59

 heroism

-0.57

Hochspringen

-0.56

DOI

-0.55

shiro

-0.52

NewUrlParser

-0.52

POSITIVE LOGITS

 annoying

2.15

 annoy

1.62

 irritating

1.58

 troublesome

1.44

 annoyance

1.38

 unpleasant

1.36

 annoys

1.36

 bothers

1.29

 bothering

1.25

 pesky

1.25

Activations Density 0.090%

terms related to annoyance or frustrating experiences

No Comments

No Known Activations