INDEX

Explanations

Twitter usernames or handles

oai_token-act-pair · gpt-3.5-turbo

mentions of specific Twitter handles or social media accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

worms

-0.95

binding

-0.75

 reciproc

-0.74

 restraints

-0.70

ciplinary

-0.70

iors

-0.70

 weaker

-0.68

entimes

-0.68

 weakest

-0.67

 controls

-0.67

POSITIVE LOGITS

FOX

1.09

 SPORTS

0.97

 Kyle

0.96

 Jonathan

0.96

 Lauren

0.95

 Katie

0.94

 Dave

0.94

 Shaun

0.92

 Laura

0.92

 Matt

0.91

Activations Density 0.018%

Twitter usernames or handles

mentions of specific Twitter handles or social media accounts

No Comments

No Known Activations