INDEX

Explanations

mentions of the concept of being or existence

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "being" or existence

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

 Mines

-0.69

yss

-0.69

éĹĺ

-0.67

 tiss

-0.67

 Nanto

-0.66

icion

-0.65

 lucrative

-0.63

 Lans

-0.63

 Regions

-0.63

mington

-0.61

POSITIVE LOGITS

 judged

0.87

 alive

0.80

hood

0.79

 immersed

0.78

who

0.77

 inhab

0.72

 sacrificed

0.71

 walked

0.71

 whom

0.71

 possessed

0.71

Activations Density 0.024%

mentions of the concept of being or existence

references to the concept of "being" or existence

No Comments

No Known Activations