INDEX

Explanations

references to rumors

oai_token-act-pair · gpt-3.5-turbo

terms related to rumors and speculation

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

artney

-0.78

DOS

-0.74

mand

-0.74

acted

-0.71

ĸļ

-0.71

alone

-0.71

nea

-0.67

ells

-0.66

asper

-0.63

itaire

-0.61

POSITIVE LOGITS

 rumors

1.11

 rumor

1.05

 rumours

1.03

 gossip

0.86

Rum

0.84

 circulating

0.81

cov

0.81

 speculation

0.78

 whispers

0.78

Rum

0.77

Activations Density 0.045%

references to rumors

terms related to rumors and speculation

No Comments

No Known Activations