INDEX

Explanations

words related to surnames or last names

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of "le" or "re" morphology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

REDACTED

-0.75

Tuc

-0.70

 Annotations

-0.70

 mastering

-0.69

 employing

-0.64

 Samar

-0.63

!/

-0.63

 Maid

-0.62

 Dollars

-0.62

 Centauri

-0.61

POSITIVE LOGITS

etooth

1.02

eps

0.93

chers

0.92

angle

0.91

pter

0.89

uler

0.89

ching

0.87

pling

0.85

ut

0.85

angles

0.85

Activations Density 0.110%

words related to surnames or last names

words related to various forms of "le" or "re" morphology

No Comments

No Known Activations