INDEX

Explanations

expressions related to taking time for something

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of taking time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ntil

-0.94

ramid

-0.93

oeuv

-0.86

ndra

-0.77

dds

-0.76

ept

-0.75

ince

-0.75

ixture

-0.74

dor

-0.71

seless

-0.71

POSITIVE LOGITS

 moder

0.86

 remed

0.79

rawdownloadcloneembedreportprint

0.78

 breat

0.75

 downtime

0.71

 away

0.71

 hiatus

0.70

ESSION

0.67

 lightly

0.66

*)

0.66

Activations Density 0.043%

expressions related to taking time for something

phrases emphasizing the concept of taking time

No Comments

No Known Activations