INDEX

Explanations

past tense verbs ending in 'ed'

oai_token-act-pair · gpt-3.5-turbo

expressions of past experiences and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

etheless

-0.77

patch

-0.64

 MacArthur

-0.62

device

-0.62

conservancy

-0.61

robat

-0.61

idon

-0.61

align

-0.60

atin

-0.60

Dru

-0.60

POSITIVE LOGITS

 marginally

0.80

ONE

0.79

 spor

0.78

ifiable

0.70

 scratched

0.66

 fraction

0.65

hig

0.65

 temporary

0.65

ered

0.63

anke

0.63

Activations Density 0.164%

past tense verbs ending in 'ed'

expressions of past experiences and actions

No Comments

No Known Activations