INDEX

Explanations

phrases related to placing responsibility or difficulty on someone or something

oai_token-act-pair · gpt-3.5-turbo

references to burdens or responsibilities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

vision

-0.75

vironment

-0.74

 rave

-0.73

regor

-0.69

naissance

-0.69

cellence

-0.68

 rall

-0.66

riber

-0.65

mpeg

-0.64

irgin

-0.63

POSITIVE LOGITS

 burden

1.23

 burdens

1.15

 borne

1.06

 imposed

1.00

ome

0.98

 levied

0.94

 incurred

0.87

 placed

0.85

 lifted

0.85

 burd

0.84

Activations Density 0.064%

phrases related to placing responsibility or difficulty on someone or something

references to burdens or responsibilities in various contexts

No Comments

No Known Activations