INDEX

Explanations

spoken and written words ending in '-st', '-ent', '-rant', or '-ist'

oai_token-act-pair · gpt-3.5-turbo

terms related to naming and identification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 loopholes

-0.62

FORMATION

-0.60

 envy

-0.59

ÙĴ

-0.59

 Duterte

-0.59

 edit

-0.59

 coli

-0.58

ModLoader

-0.58

":[

-0.57

 LEVEL

-0.57

POSITIVE LOGITS

gaard

0.94

ensen

0.92

baugh

0.91

opoulos

0.90

rup

0.88

eer

0.88

feld

0.87

cia

0.87

cki

0.87

enburg

0.86

Activations Density 0.191%

spoken and written words ending in '-st', '-ent', '-rant', or '-ist'

terms related to naming and identification

No Comments

No Known Activations