INDEX

Explanations

words related to positions or stances in discussions or debates

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "position" 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

rosso

-0.79

 Bagg

-0.71

STON

-0.70

displayText

-0.69

ebook

-0.67

ilation

-0.65

NetMessage

-0.64

ãĥ¼ãĥĨãĤ£

-0.64

isdom

-0.63

oa

-0.63

POSITIVE LOGITS

 positions

1.24

 position

1.18

holders

1.11

holder

1.01

 stances

0.87

 holders

0.86

quo

0.84

 holder

0.84

iton

0.81

 plank

0.80

Activations Density 0.025%

words related to positions or stances in discussions or debates

occurrences of the word "position" in various contexts

No Comments

No Known Activations