INDEX

Explanations

phrases related to questioning or disproving information, myths, or theories

oai_token-act-pair · gpt-3.5-turbo

terms related to debunking and disproving myths or misconceptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arta

-0.77

ebus

-0.72

estate

-0.67

emetery

-0.67

 actionGroup

-0.66

ãĤ¼ãĤ¦ãĤ¹

-0.62

estial

-0.61

orneys

-0.61

enos

-0.59

ertility

-0.58

POSITIVE LOGITS

 unfounded

0.85

 rumours

0.82

 debunked

0.82

 debunk

0.78

arthed

0.77

itely

0.77

ument

0.77

 rumors

0.74

idated

0.74

 allegations

0.73

Activations Density 0.088%

phrases related to questioning or disproving information, myths, or theories

terms related to debunking and disproving myths or misconceptions

No Comments

No Known Activations