INDEX

Explanations

words related to making comments or statements

oai_token-act-pair · gpt-3.5-turbo

instances of commentary or statements regarding an issue

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

illac

-0.82

PLIED

-0.76

MAP

-0.73

INFO

-0.72

BuyableInstoreAndOnline

-0.69

ModLoader

-0.67

Definition

-0.67

WARN

-0.67

LOG

-0.66

STD

-0.66

POSITIVE LOGITS

 behalf

1.17

ariat

0.79

 anonymously

0.64

election

0.64

 matters

0.63

eless

0.62

orate

0.62

wards

0.62

 regretted

0.62

 karma

0.62

Activations Density 0.092%

words related to making comments or statements

instances of commentary or statements regarding an issue

No Comments

No Known Activations