INDEX

Explanations

words related to rumors or unconfirmed information

oai_token-act-pair · gpt-3.5-turbo

references 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pex

-0.74

ĸļ

-0.71

elsh

-0.71

Interstitial

-0.69

 Governors

-0.68

drivers

-0.65

alone

-0.64

nice

-0.63

ĪĴ

-0.62

EVA

-0.61

POSITIVE LOGITS

 swirling

1.16

 circulating

1.13

 rumors

1.13

 rumor

1.12

 rumours

1.06

 surrounding

1.03

 circulated

1.01

 swirl

0.99

 circling

0.98

 regarding

0.96

Activations Density 0.107%

words related to rumors or unconfirmed information

references to rumors and speculation

No Comments

No Known Activations