INDEX

Explanations

words related to data analysis and database operations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Revival

-0.85

mods

-0.74

acia

-0.74

lord

-0.73

Dialogue

-0.73

Rez

-0.73

Fight

-0.71

pite

-0.68

 Rebell

-0.67

#$#$

-0.65

POSITIVE LOGITS

 statistical

1.26

 analytics

1.23

 data

1.21

 database

1.17

 databases

1.10

 dataset

1.05

analy

1.05

 predictive

1.04

 datasets

1.04

 statistics

1.03

Activations Density 0.700%

words related to data analysis and database operations

No Comments

No Known Activations