INDEX

Explanations

critiques or negative sentiments in text

oai_token-act-pair · gpt-3.5-turbo

phrases related to skepticism or criticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

naissance

-0.66

 gorgeous

-0.66

 Gorge

-0.64

thood

-0.64

 civilisation

-0.63

 virginity

-0.62

 burgeoning

-0.60

 glamorous

-0.60

 paradise

-0.60

 badass

-0.60

POSITIVE LOGITS

 amendment

0.76

Statement

0.74

Senator

0.73

phr

0.70

 wording

0.70

 briefed

0.69

Chair

0.68

 Counsel

0.68

 counsel

0.67

 Reporter

0.67

Activations Density 1.507%

critiques or negative sentiments in text

phrases related to skepticism or criticism

No Comments

No Known Activations