INDEX

Explanations

references to continuing or persisting actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating continuity or ongoing actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Surprise

-0.81

soDeliveryDate

-0.73

 Yosemite

-0.72

 Mesa

-0.69

 Abdel

-0.68

 Sierra

-0.68

 gems

-0.65

 Clothing

-0.65

Bet

-0.63

 Fancy

-0.62

POSITIVE LOGITS

 uninterrupted

0.96

 adolesc

0.85

abre

0.81

 footsteps

0.79

 tradition

0.77

 downward

0.73

liction

0.73

 steady

0.72

 unchanged

0.71

 trend

0.71

Activations Density 0.157%

references to continuing or persisting actions

phrases indicating continuity or ongoing actions

No Comments

No Known Activations