INDEX

Explanations

terms related to promoting or endorsement

oai_token-act-pair · gpt-3.5-turbo

words related to the act of promoting or advocating for various causes and initiatives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quartered

-0.67

fighters

-0.65

Oo

-0.64

soon

-0.62

asso

-0.61

 Cage

-0.61

------------------------------------------------

-0.59

 Caps

-0.58

 slightest

-0.58

avier

-0.58

POSITIVE LOGITS

ably

0.84

entious

0.82

glomer

0.81

 promoting

0.79

ifference

0.76

 promotion

0.74

interstitial

0.73

 tremend

0.72

hovah

0.72

andise

0.71

Activations Density 0.029%

terms related to promoting or endorsement

words related to the act of promoting or advocating for various causes and initiatives

No Comments

No Known Activations