INDEX

Explanations

phrases indicating lack of relationship or connection between entities

oai_token-act-pair · gpt-3.5-turbo

repeated phrases emphasizing a disconnect between events and personal or contextual influences

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

©¶æ¥µ

-0.81

warn

-0.75

kept

-0.74

MAP

-0.72

Released

-0.71

jab

-0.71

STAT

-0.68

ura

-0.68

NN

-0.67

 Ahead

-0.66

POSITIVE LOGITS

 what

0.74

 determining

0.72

erous

0.68

orno

0.66

 whether

0.65

 regard

0.64

 automobiles

0.62

 entitle

0.60

 fiat

0.60

 whatsoever

0.60

Activations Density 0.033%

phrases indicating lack of relationship or connection between entities

repeated phrases emphasizing a disconnect between events and personal or contextual influences

No Comments

No Known Activations