INDEX

Explanations

phrases related to time measurements, specifically focusing on "hours"

oai_token-act-pair · gpt-3.5-turbo

references to work hours and time constraints

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

dinand

-1.12

iors

-0.84

LECT

-0.83

ften

-0.78

esan

-0.75

iour

-0.74

reditary

-0.73

analysis

-0.73

IFIC

-0.72

ortium

-0.70

POSITIVE LOGITS

glass

1.02

endment

0.87

mith

0.76

uty

0.75

lot

0.73

pring

0.71

 commute

0.70

linger

0.70

aving

0.69

ness

0.69

Activations Density 0.030%

phrases related to time measurements, specifically focusing on "hours"

references to work hours and time constraints

No Comments

No Known Activations