INDEX

Explanations

proper nouns and named entities

oai_token-act-pair · gpt-3.5-turbo

specific jargon or terminology related to topics in the arts, media, and politics

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

 wise

-0.64

theless

-0.56

 sales

-0.50

ifully

-0.48

[+

-0.47

 trave

-0.47

itably

-0.47

istically

-0.47

QC

-0.46

rely

-0.46

POSITIVE LOGITS

iverse

0.74

iphate

0.70

idae

0.68

psons

0.66

agonist

0.66

ndum

0.65

iest

0.65

 logo

0.63

onian

0.63

osphere

0.63

Activations Density 0.697%

proper nouns and named entities

specific jargon or terminology related to topics in the arts, media, and politics

No Comments

No Known Activations