INDEX

Explanations

phrases related to large-scale events or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to large-scale occurrences or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

emis

-0.77

vous

-0.74

vice

-0.67

gnu

-0.66

nces

-0.65

onso

-0.64

iour

-0.64

cair

-0.63

 Nich

-0.62

Reviewed

-0.62

POSITIVE LOGITS

 scale

1.22

 quantities

1.13

 intestine

1.12

 amounts

1.05

 swat

1.03

 swath

1.02

 quantity

1.01

pox

0.99

(>

0.98

 enough

0.97

Activations Density 0.064%

phrases related to large-scale events or entities

terms related to large-scale occurrences or issues

No Comments

No Known Activations