INDEX

Explanations

the keyword "ILA"

oai_token-act-pair · gpt-3.5-turbo

the term "ILA" and related acronyms or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Chancellor

-0.71

 Ridley

-0.71

 Prophet

-0.66

ger

-0.65

irect

-0.64

 Monarch

-0.64

 Twin

-0.64

mart

-0.64

 virgin

-0.64

conscious

-0.63

POSITIVE LOGITS

ILA

4.88

ICS

1.37

ICA

1.31

ISA

1.25

ARA

1.19

ICO

1.10

ESA

1.09

annie

1.07

API

1.06

 amnesty

1.06

Activations Density 0.055%

the keyword "ILA"

the term "ILA" and related acronyms or identifiers

No Comments

No Known Activations