INDEX

Explanations

phrases containing the word 'wondered'

oai_token-act-pair · gpt-3.5-turbo

phrases that express curiosity or contemplation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.86

ccording

-0.82

interstitial

-0.77

apsed

-0.69

enses

-0.68

Ĥ¬

-0.67

cephal

-0.62

estial

-0.62

ensed

-0.62

utable

-0.61

POSITIVE LOGITS

 aloud

1.05

why

0.86

INGTON

0.81

ingly

0.81

how

0.80

why

0.76

 wonder

0.76

 wondering

0.75

warts

0.74

 whether

0.74

Activations Density 0.026%

phrases containing the word 'wondered'

phrases that express curiosity or contemplation

No Comments

No Known Activations