INDEX

Explanations

mentions of Rupert Murdoch

oai_token-act-pair · gpt-3.5-turbo

references to Rupert Murdoch and associated media entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

RNA

-0.83

soDeliveryDate

-0.76

ranged

-0.76

othing

-0.74

activated

-0.72

cession

-0.70

wives

-0.70

venge

-0.68

errors

-0.68

testing

-0.67

POSITIVE LOGITS

 Murdoch

1.36

doms

0.94

 Tycoon

0.89

sonian

0.86

emouth

0.80

minster

0.80

IES

0.77

mog

0.76

enthal

0.76

vertising

0.75

Activations Density 0.036%

mentions of Rupert Murdoch

references to Rupert Murdoch and associated media entities

No Comments

No Known Activations