INDEX

Explanations

words associated with negative consequences or outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating causality or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

afort

-0.64

 Shal

-0.64

iling

-0.62

pload

-0.62

 Vaughn

-0.60

terday

-0.59

 Sunshine

-0.58

 Scotia

-0.58

atu

-0.57

 tuber

-0.57

POSITIVE LOGITS

gers

0.91

entious

0.88

wcs

0.84

better

0.77

-+

0.76

iments

0.74

ges

0.71

ging

0.70

rush

0.68

GGGG

0.67

Activations Density 0.031%

words associated with negative consequences or outcomes

phrases indicating causality or consequences

No Comments

No Known Activations