INDEX

Explanations

words related to misinformation and deception

oai_token-act-pair · gpt-3.5-turbo

phrases related to falsehoods or misinformation

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

hens

-1.03

 guiActiveUnfocused

-0.92

hetti

-0.88

ajo

-0.79

mun

-0.77

aldo

-0.76

ODY

-0.75

xual

-0.75

APTER

-0.73

rador

-0.72

POSITIVE LOGITS

 positives

1.02

 accuser

0.85

 guiActiveUn

0.84

 false

0.82

 dich

0.81

 falsely

0.76

 unfocusedRange

0.75

 guiIcon

0.73

 negatives

0.72

 assumptions

0.72

Activations Density 0.019%

words related to misinformation and deception

phrases related to falsehoods or misinformation

No Comments

No Known Activations