INDEX

Explanations

expressions related to construction and building

oai_token-act-pair · gpt-3.5-turbo

specific company names and related entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

querque

-0.65

ufact

-0.63

vertisement

-0.61

ubi

-0.58

arcity

-0.54

icipated

-0.54

assador

-0.54

 Lauder

-0.52

isible

-0.51

anwhile

-0.51

POSITIVE LOGITS

 Poles

0.57

hei

0.55

wagen

0.53

 edges

0.52

nels

0.49

lde

0.48

âĦ¢:

0.48

Â´

0.48

Scale

0.48

 polyg

0.47

Activations Density 1.287%

expressions related to construction and building

specific company names and related entities

No Comments

No Known Activations