INDEX

Explanations

phrases related to specific products or brands, particularly related to technology and food

oai_token-act-pair · gpt-3.5-turbo

references to specific food items or brands

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

 Lauder

-0.69

 testament

-0.69

writers

-0.67

agents

-0.66

 tracts

-0.65

affe

-0.64

writer

-0.63

 Confeder

-0.63

funding

-0.62

rers

-0.62

POSITIVE LOGITS

ipop

0.83

olini

0.82

ical

0.79

orrow

0.79

keley

0.77

Reviewer

0.75

aceutical

0.74

ucci

0.74

icum

0.73

Activations Density 0.051%

phrases related to specific products or brands, particularly related to technology and food

references to specific food items or brands

No Comments

No Known Activations