INDEX

Explanations

periods

oai_token-act-pair · gpt-3.5-turbo

sentences that conclude or summarize information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 challeng

-0.79

otin

-0.76

anting

-0.74

 sustainability

-0.69

iver

-0.69

 nurt

-0.69

 integ

-0.68

 embodied

-0.68

 regener

-0.67

 stubborn

-0.67

POSITIVE LOGITS

 However

1.12

 Afterwards

1.09

 Others

1.04

 Later

1.03

 Then

1.00

 Also

0.99

 Officials

0.97

 Seems

0.96

 They

0.96

 Apparently

0.95

Activations Density 0.392%

periods

sentences that conclude or summarize information

No Comments

No Known Activations