INDEX

Explanations

verbs indicating movement or travel to a specific location

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "to"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hops

-0.66

interstitial

-0.66

pie

-0.59

holes

-0.59

 surges

-0.59

yellow

-0.57

rag

-0.56

 flakes

-0.56

 Hebdo

-0.56

 airs

-0.55

POSITIVE LOGITS

 ensure

1.05

 avoid

1.01

 accommodate

1.01

 promote

1.01

 maximize

1.00

 relieve

1.00

 facilitate

0.98

 satisfy

0.95

 celebrate

0.94

 give

0.94

Activations Density 0.209%

verbs indicating movement or travel to a specific location

occurrences of the word "to"

No Comments

No Known Activations