INDEX

Explanations

phrases starting with "In" followed by personal experiences or reflections

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "In" followed by various contexts or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 endors

-0.64

 implicated

-0.62

 jointly

-0.61

 fugitive

-0.60

ITE

-0.59

 homegrown

-0.58

 unveiled

-0.58

AAF

-0.57

 soar

-0.57

 extensively

-0.57

POSITIVE LOGITS

 hindsight

1.39

 spite

1.29

 fact

1.27

 retrospect

1.21

juries

1.14

cluding

1.09

jured

1.09

 lieu

1.07

advert

1.06

visible

1.01

Activations Density 0.200%

phrases starting with "In" followed by personal experiences or reflections

occurrences of the phrase "In" followed by various contexts or statements

No Comments

No Known Activations