INDEX

Explanations

words related to speed or quickness

oai_token-act-pair · gpt-3.5-turbo

instances of the word "quickly" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

liga

-0.84

pel

-0.78

raints

-0.77

icion

-0.76

Ãį

-0.72

artisan

-0.71

unal

-0.71

adata

-0.69

pheus

-0.68

ornia

-0.68

POSITIVE LOGITS

 paced

0.97

aneously

0.95

 enough

0.92

idious

0.84

ened

0.78

 approaching

0.77

 thereafter

0.76

 turnaround

0.74

 deterior

0.73

 asleep

0.72

Activations Density 0.023%

words related to speed or quickness

instances of the word "quickly" in various contexts

No Comments

No Known Activations