INDEX

Explanations

phrases related to time spent or duration

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spent" indicating time expenditure

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seymour

-0.63

 detonated

-0.61

 Watson

-0.58

 Conan

-0.56

 Edmund

-0.55

peer

-0.55

 conver

-0.54

ensen

-0.54

ĪĴ

-0.54

 Cassandra

-0.53

POSITIVE LOGITS

itures

0.92

lav

0.91

IPM

0.86

ãĤ£

0.76

iture

0.75

 beads

0.75

htaking

0.72

#$#$

0.71

edIn

0.71

zl

0.69

Activations Density 0.028%

phrases related to time spent or duration

instances of the word "spent" indicating time expenditure

No Comments

No Known Activations