INDEX

Explanations

phrases indicating impact or influence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "affected" or similar terms indicating impact on individuals or groups

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

çĦ

-0.74

YC

-0.71

OVA

-0.71

cia

-0.68

WithNo

-0.68

otten

-0.68

ope

-0.66

ATT

-0.63

IFE

-0.62

outh

-0.61

POSITIVE LOGITS

 adversely

0.98

 affected

0.88

 effected

0.79

 impacted

0.78

 havoc

0.77

 impacts

0.76

 negatively

0.75

 impact

0.69

 unaffected

0.68

 hemor

0.67

Activations Density 0.052%

phrases indicating impact or influence

instances of the word "affected" or similar terms indicating impact on individuals or groups

No Comments

No Known Activations