INDEX

Explanations

mentions of a specific type of clothing item

oai_token-act-pair · gpt-3.5-turbo

words related to psychological concepts or analysis

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

 Rail

-0.64

 visas

-0.63

met

-0.62

NS

-0.60

 visa

-0.58

 royal

-0.58

 istg

-0.58

 occurred

-0.58

 penetration

-0.57

 registered

-0.57

POSITIVE LOGITS

cho

4.66

CHO

2.00

Cho

1.56

choice

1.48

ch

1.36

Cho

1.36

CHO

1.32

vo

1.24

cho

1.24

cher

1.20

Activations Density 0.022%

mentions of a specific type of clothing item

words related to psychological concepts or analysis

No Comments

No Known Activations