INDEX

Explanations

words related to Ireland or the Irish

oai_token-act-pair · gpt-3.5-turbo

references to Irish identity or related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĸļ

-0.86

nels

-0.84

eger

-0.79

PsyNetMessage

-0.79

iguous

-0.79

inventoryQuantity

-0.79

lished

-0.78

insula

-0.77

eters

-0.75

aturdays

-0.74

POSITIVE LOGITS

man

0.88

 Examiner

0.82

 Catholic

0.81

 moss

0.78

 Gael

0.78

men

0.77

lean

0.77

oslov

0.77

 Catholics

0.76

 Volunteers

0.75

Activations Density 0.018%

words related to Ireland or the Irish

references to Irish identity or related content

No Comments

No Known Activations