INDEX

Explanations

terms related to being associated or connected with an organization or group

oai_token-act-pair · gpt-3.5-turbo

instances of the word "affiliated" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

oufl

-0.72

othy

-0.68

Detailed

-0.67

raq

-0.67

=-=-=-=-=-=-=-=-

-0.66

pter

-0.64

ppy

-0.63

abytes

-0.63

assert

-0.63

 curv

-0.62

POSITIVE LOGITS

hips

1.19

 affili

1.13

 affiliated

1.12

 affiliation

1.04

iliated

1.02

lia

0.99

nect

0.86

 affiliate

0.79

iance

0.78

affiliated

0.76

Activations Density 0.031%

terms related to being associated or connected with an organization or group

instances of the word "affiliated" and its variations

No Comments

No Known Activations