INDEX

Explanations

phrases or sentences expressing future predictions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating future actions or events

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

coni

-0.68

ihad

-0.62

lude

-0.59

cano

-0.57

furt

-0.56

illery

-0.56

uminati

-0.56

krit

-0.54

 recalls

-0.54

lake

-0.53

POSITIVE LOGITS

to

1.05

 nowhere

0.94

 downhill

0.81

 extinct

0.74

to

0.72

TO

0.71

 overboard

0.70

 uphill

0.68

©¶æ

0.67

 viral

0.66

Activations Density 0.044%

phrases or sentences expressing future predictions

phrases indicating future actions or events

No Comments

No Known Activations