INDEX

Explanations

activities or events ending in 'ing'

oai_token-act-pair · gpt-3.5-turbo

words related to listening and streaming activities

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

grave

-0.66

 synerg

-0.66

 surg

-0.65

iola

-0.64

 insign

-0.64

lda

-0.64

 claw

-0.64

 suff

-0.63

lein

-0.62

 foundations

-0.62

POSITIVE LOGITS

 Parties

0.73

ople

0.70

Companies

0.69

 Reviews

0.67

 VIDEOS

0.67

mitt

0.67

ording

0.66

 Videos

0.66

Service

0.65

 streamed

0.65

Activations Density 0.193%

activities or events ending in 'ing'

words related to listening and streaming activities

No Comments

No Known Activations