INDEX

Explanations

mentions of the word "flush."

oai_token-act-pair · gpt-3.5-turbo

references to the term "flush."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Attribution

-0.69

 lawy

-0.69

Theme

-0.67

lder

-0.63

oret

-0.61

 theoret

-0.60

 illust

-0.60

evidence

-0.58

ctive

-0.58

 illustration

-0.57

POSITIVE LOGITS

 flush

2.82

flush

1.21

 Bliss

0.78

lease

0.66

Hai

0.66

acements

0.64

cffff

0.64

 wipe

0.63

independence

0.62

FK

0.61

Activations Density 0.000%

mentions of the word "flush."

references to the term "flush."

No Comments

No Known Activations