INDEX

Explanations

mentions of the origin or source of something

oai_token-act-pair · gpt-3.5-turbo

the word "from" used repeatedly in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ratulations

-0.72

seek

-0.69

priority

-0.65

aqu

-0.65

few

-0.64

merce

-0.64

iar

-0.64

bably

-0.63

istar

-0.63

sat

-0.62

POSITIVE LOGITS

 afar

1.34

 whence

1.13

 thence

1.07

 abroad

0.96

 scratch

0.86

 anywhere

0.81

 somewhere

0.80

 elsewhere

0.79

 inside

0.79

 Frie

0.78

Activations Density 0.220%

mentions of the origin or source of something

the word "from" used repeatedly in various contexts

No Comments

No Known Activations