INDEX

Explanations

phrases starting with "After"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "After" followed by numerical values indicating time frames or sequences

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

å¥³

-0.74

 constitu

-0.70

IZE

-0.69

âģ

-0.66

Especially

-0.65

MENT

-0.62

 unfocusedRange

-0.62

NRS

-0.62

ï¿½ï¿½ï¿½ï¿½

-0.61

eto

-0.60

POSITIVE LOGITS

wards

1.29

noon

1.28

ward

1.25

math

1.23

word

1.00

words

0.97

 graduating

0.86

 awhile

0.82

market

0.82

shock

0.80

Activations Density 0.069%

phrases starting with "After"

instances of the word "After" followed by numerical values indicating time frames or sequences

No Comments

No Known Activations