INDEX

Explanations

quantitative terms or descriptions in texts

oai_token-act-pair · gpt-3.5-turbo

references to quantity and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

boa

-0.69

ARP

-0.68

stal

-0.65

nee

-0.64

INA

-0.62

ramid

-0.62

 namesake

-0.62

zbollah

-0.61

oe

-0.61

ODE

-0.61

POSITIVE LOGITS

 quantity

1.24

 quantities

1.16

quant

0.92

Quantity

0.90

itatively

0.86

odynam

0.78

ngth

0.77

ickr

0.76

catentry

0.76

 quotas

0.75

Activations Density 0.008%

quantitative terms or descriptions in texts

references to quantity and measurement

No Comments

No Known Activations