INDEX

Explanations

words related to loss or potential detriment

oai_token-act-pair · gpt-3.5-turbo

instances of the words "lose" and "losing" that convey the concept of loss or absence

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

sis

-0.68

opot

-0.66

 Aires

-0.65

orig

-0.64

 Janeiro

-0.63

 Municip

-0.62

Loading

-0.61

osi

-0.61

Grab

-0.60

ature

-0.60

POSITIVE LOGITS

 aversion

0.81

esty

0.75

esses

0.74

itaire

0.74

 virginity

0.73

 sight

0.73

veyard

0.72

 souls

0.72

luster

0.70

 streaks

0.69

Activations Density 0.030%

words related to loss or potential detriment

instances of the words "lose" and "losing" that convey the concept of loss or absence

No Comments

No Known Activations