INDEX

Explanations

phrases involving prepositions followed by a name or a pronoun

oai_token-act-pair · gpt-3.5-turbo

references to specific groups and their attitudes or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

obin

-0.75

avis

-0.74

resses

-0.67

%%%%

-0.66

 guiActiveUn

-0.66

activate

-0.63

roup

-0.61

ASS

-0.60

bernatorial

-0.60

onew

-0.60

POSITIVE LOGITS

nen

0.65

there

0.64

gaard

0.63

it

0.62

 however

0.58

enment

0.58

çīĪ

0.57

anes

0.57

 Frankfurt

0.56

 seeing

0.56

Activations Density 0.174%

phrases involving prepositions followed by a name or a pronoun

references to specific groups and their attitudes or actions

No Comments

No Known Activations