INDEX

Explanations

technical terms related to computer systems or programming

oai_token-act-pair · gpt-3.5-turbo

references to technologies and their abbreviations

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

 closures

-0.74

 trave

-0.69

 caring

-0.69

 vacuum

-0.68

 refres

-0.68

 minim

-0.67

 settlements

-0.66

 debugging

-0.66

 commuting

-0.65

 decon

-0.65

POSITIVE LOGITS

ZX

1.35

kj

1.28

wx

1.26

FK

1.26

FH

1.25

zx

1.23

OX

1.23

_-

1.23

qq

1.21

UX

1.21

Activations Density 0.034%

technical terms related to computer systems or programming

references to technologies and their abbreviations

No Comments

No Known Activations