INDEX

Explanations

technical terms related to electronics and devices

oai_token-act-pair · gpt-3.5-turbo

negative values or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 bounce

-0.84

 Arabian

-0.75

 square

-0.73

rou

-0.72

 hiber

-0.71

 scrim

-0.71

 Blizz

-0.69

scr

-0.69

sep

-0.68

 resort

-0.68

POSITIVE LOGITS

III

1.22

FM

1.18

II

1.17

LIB

1.10

LI

1.08

1.07

IV

1.06

1.05

Activations Density 0.085%

technical terms related to electronics and devices

negative values or concepts

No Comments

No Known Activations