INDEX

Explanations

mentions of advertisements

oai_token-act-pair · gpt-3.5-turbo

terms related to advertising and promotional content

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

uckle

-0.80

steen

-0.74

-0.70

kson

-0.66

ologically

-0.66

come

-0.65

 Morrow

-0.64

borg

-0.63

izers

-0.60

opez

-0.60

POSITIVE LOGITS

vertising

1.07

 Advertisement

0.99

culosis

0.86

allery

0.81

VERTISEMENT

0.80

 advertisement

0.76

FontSize

0.75

eering

0.74

agascar

0.74

elaide

0.74

Activations Density 0.020%

mentions of advertisements

terms related to advertising and promotional content

No Comments

No Known Activations