INDEX

Explanations

references or mentions of rumors

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Rum" and context related to rumors or misinformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 humans

-0.68

activated

-0.65

athetic

-0.64

 autism

-0.63

 human

-0.62

 Annotations

-0.62

chnology

-0.61

 Wildcats

-0.61

ACP

-0.61

Interstitial

-0.61

POSITIVE LOGITS

Rum

1.16

Rum

1.11

atis

0.83

uz

0.83

inating

0.80

ussia

0.80

 unden

0.79

rum

0.79

aji

0.78

jah

0.75

Activations Density 0.009%

references or mentions of rumors

occurrences of the word "Rum" and context related to rumors or misinformation

No Comments

No Known Activations