INDEX

Explanations

mentions of new items, changes, or developments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "new" in the context of proposed changes or updates

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

Zip

-0.83

ONSORED

-0.79

ashtra

-0.75

acebook

-0.74

lua

-0.74

uddin

-0.72

cius

-0.71

thia

-0.71

IQ

-0.68

ARA

-0.68

POSITIVE LOGITS

bie

1.23

bies

1.20

 arrivals

1.10

 additions

0.99

 edition

0.95

 generation

0.91

 batch

0.91

 millennium

0.91

 entrants

0.88

 developments

0.87

Activations Density 0.077%

mentions of new items, changes, or developments

occurrences of the word "new" in the context of proposed changes or updates

No Comments

No Known Activations