INDEX

Explanations

numbers and measurements

oai_token-act-pair · gpt-3.5-turbo

specific terms related to spatial measurements and guest-related themes

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

 timelines

-0.70

rencies

-0.68

 establishments

-0.67

 finances

-0.64

 Surve

-0.63

 classes

-0.62

rities

-0.61

tics

-0.61

rooms

-0.61

 gatherings

-0.61

POSITIVE LOGITS

 apiece

0.70

abyte

0.69

dozen

0.67

less

0.67

TPPStreamerBot

0.63

 reminder

0.63

alyst

0.63

 approximation

0.62

hole

0.62

iom

0.60

Activations Density 0.677%

numbers and measurements

specific terms related to spatial measurements and guest-related themes

No Comments

No Known Activations