INDEX

Explanations

specific numerical values or measurements mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

references to seasons in a series or program

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Afric

-0.58

Iss

-0.57

idia

-0.56

 scapego

-0.55

)?

-0.54

 Rodrigo

-0.54

oint

-0.54

 sided

-0.53

learning

-0.52

bit

-0.51

POSITIVE LOGITS

 predecessors

1.33

 counterparts

1.20

 previous

1.20

 traditional

1.16

 normally

1.15

 conventional

1.14

 usual

1.12

 predecessor

1.08

 competitors

1.07

 ordinarily

1.07

Activations Density 1.115%

specific numerical values or measurements mentioned in a text

references to seasons in a series or program

No Comments

No Known Activations