INDEX

Explanations

moments expressing a pause or reflection in a text

oai_token-act-pair · gpt-3.5-turbo

references to time-related pauses or reflective moments

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

grades

-0.70

uces

-0.69

 scores

-0.68

agles

-0.64

 subordinates

-0.62

 fitt

-0.62

kefeller

-0.62

licts

-0.62

comes

-0.62

models

-0.62

POSITIVE LOGITS

 glance

0.82

aire

0.79

 pause

0.77

 apiece

0.76

hander

0.74

ago

0.73

 lick

0.69

ary

0.69

glass

0.68

hower

0.68

Activations Density 0.075%

moments expressing a pause or reflection in a text

references to time-related pauses or reflective moments

No Comments

No Known Activations