INDEX

Explanations

invitations or events that involve participation or attendance

oai_token-act-pair · gpt-3.5-turbo

references to invitations or events that involve participation or acknowledgment

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

Ĥ¬

-0.79

Ħ¢

-0.76

dress

-0.68

 separating

-0.67

grass

-0.67

¥µ

-0.65

 cleaner

-0.65

 horizontally

-0.64

©¶æ

-0.63

bian

-0.63

POSITIVE LOGITS

itations

1.36

incible

1.31

itational

1.30

asion

1.26

igor

1.22

itation

1.19

ulnerable

1.17

asions

1.15

olve

1.13

olved

1.12

Activations Density 0.011%

invitations or events that involve participation or attendance

references to invitations or events that involve participation or acknowledgment

No Comments

No Known Activations