INDEX

Explanations

the word "something"

oai_token-act-pair · gpt-3.5-turbo

mentions of 'something,' indicating a focus on unspecified or abstract concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ortex

-0.72

anos

-0.71

ardi

-0.69

phones

-0.68

 Sprint

-0.68

nor

-0.65

anism

-0.65

 Chiefs

-0.64

inders

-0.64

ocytes

-0.64

POSITIVE LOGITS

 else

1.43

Else

1.33

 resembling

1.07

 worthwhile

0.86

 Else

0.85

 intangible

0.84

 miraculous

0.83

iverse

0.81

 akin

0.81

 tangible

0.81

Activations Density 0.067%

the word "something"

mentions of 'something,' indicating a focus on unspecified or abstract concepts

No Comments

No Known Activations