INDEX

Explanations

words related to vehicles and transportation

oai_token-act-pair · gpt-3.5-turbo

suffixes related to diminutive or affectionate forms, often ending in 'ie' or 'y'

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

 Cosponsors

-0.84

fman

-0.78

itures

-0.78

imester

-0.77

ictional

-0.76

ername

-0.76

mental

-0.76

CHA

-0.75

ascript

-0.75

nih

-0.72

POSITIVE LOGITS

velt

0.70

Mania

0.70

 Richie

0.69

 Wally

0.66

mond

0.66

wegian

0.64

bow

0.64

bows

0.62

 Miles

0.61

 Amos

0.61

Activations Density 0.163%

words related to vehicles and transportation

suffixes related to diminutive or affectionate forms, often ending in 'ie' or 'y'

No Comments

No Known Activations