INDEX

Explanations

personal interactions, conflicts, and emotional reactions

oai_token-act-pair · gpt-3.5-turbo

references to relationships and emotional responses

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Enhance

-0.69

imum

-0.63

 Header

-0.62

ãĥ¡

-0.61

eatures

-0.61

 Depth

-0.60

 Ranking

-0.60

ãĥĳ

-0.59

Rank

-0.59

native

-0.59

POSITIVE LOGITS

 refused

1.36

 intervened

1.31

 objected

1.22

 begged

1.21

 resorted

1.21

 protested

1.20

 persisted

1.19

 yelled

1.18

 insisted

1.17

 resisted

1.17

Activations Density 0.340%

personal interactions, conflicts, and emotional reactions

references to relationships and emotional responses

No Comments

No Known Activations