INDEX

Explanations

words related to computer technology and programming languages

oai_token-act-pair · gpt-3.5-turbo

the word "up" in various contexts and forms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Caldwell

-0.66

 Rosenthal

-0.66

 sting

-0.62

 Baghd

-0.61

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.60

 Curiosity

-0.59

 Canary

-0.59

 Schwe

-0.58

KH

-0.57

 Geneva

-0.55

POSITIVE LOGITS

dates

1.60

dating

1.34

stairs

1.32

grades

1.29

olicy

1.21

graded

1.21

grade

1.19

grading

1.15

np

1.08

grad

1.04

Activations Density 0.054%

words related to computer technology and programming languages

the word "up" in various contexts and forms

No Comments

No Known Activations