INDEX

Explanations

adverbs ending in 'ly'

oai_token-act-pair · gpt-3.5-turbo

adverbs

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

ilater

-0.83

icket

-0.74

unta

-0.70

ngth

-0.69

 Mickey

-0.68

ococ

-0.68

BAT

-0.67

 Jewel

-0.66

leground

-0.65

eers

-0.64

POSITIVE LOGITS

 speaking

0.89

entimes

0.80

tics

0.76

few

0.76

than

0.70

 suffice

0.66

zed

0.65

 translated

0.64

adv

0.64

 sized

0.64

Activations Density 0.032%

adverbs ending in 'ly'

adverbs

No Comments

No Known Activations