INDEX

Explanations

mentions of follow-up activities or events

oai_token-act-pair · gpt-3.5-turbo

references to follow-up actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Fidel

-0.66

zh

-0.63

 trembling

-0.62

MAS

-0.60

 crystal

-0.60

 downt

-0.60

vez

-0.59

 slee

-0.59

 heed

-0.59

 ï¿½

-0.59

POSITIVE LOGITS

dates

1.30

dating

1.11

stairs

0.95

olicy

0.83

landish

0.82

rison

0.82

option

0.82

etric

0.79

olescent

0.79

oons

0.78

Activations Density 0.035%

mentions of follow-up activities or events

references to follow-up actions or events

No Comments

No Known Activations