INDEX

Explanations

words related to someone's name

oai_token-act-pair · gpt-3.5-turbo

instances of the abbreviation "tt" associated with various contexts or topics

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

actionDate

-0.72

 exha

-0.68

¥ŀ

-0.65

 distilled

-0.64

IRC

-0.64

STATE

-0.64

 Galile

-0.62

 psychiat

-0.62

 Paraly

-0.62

 propensity

-0.61

POSITIVE LOGITS

oken

0.99

achment

0.99

ail

0.96

uning

0.96

itle

0.95

sburgh

0.94

ilts

0.93

iquette

0.92

olkien

0.89

ilton

0.89

Activations Density 0.012%

words related to someone's name

instances of the abbreviation "tt" associated with various contexts or topics

No Comments

No Known Activations