INDEX

Explanations

information related to anonymous sources

oai_token-act-pair · gpt-3.5-turbo

references to the concept of anonymity

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

neys

-0.91

ney

-0.89

charg

-0.83

agne

-0.80

nant

-0.74

ingham

-0.71

union

-0.69

kie

-0.68

yg

-0.68

nard

-0.67

POSITIVE LOGITS

 anonymity

1.20

ously

1.09

 anonym

0.93

 anonymously

0.78

onym

0.77

efeated

0.77

 guiActiveUn

0.75

 shrouded

0.73

 immunity

0.71

 afforded

0.68

Activations Density 0.012%

information related to anonymous sources

references to the concept of anonymity

No Comments

No Known Activations