INDEX

Explanations

personal pronouns and phrases related to relationships

oai_token-act-pair · gpt-3.5-turbo

expressions of personal relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 hindsight

-0.68

 Predict

-0.65

CLAIM

-0.64

 Deadline

-0.64

 retrospect

-0.62

 Â®

-0.57

 Dirty

-0.57

DU

-0.56

EFF

-0.56

 retrospective

-0.55

POSITIVE LOGITS

 adore

0.82

."[

0.79

.'"

0.79

 âĢ¦"

0.78

 insepar

0.78

)."

0.78

]."

0.77

'."

0.74

."

0.74

 kisses

0.73

Activations Density 0.926%

personal pronouns and phrases related to relationships

expressions of personal relationships and connections

No Comments

No Known Activations