INDEX

Explanations

adjectives describing the intensity or significance of potential consequences or impacts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the impact or consequences of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

erville

-0.79

 Franch

-0.77

 mant

-0.73

etsk

-0.72

uese

-0.71

dit

-0.69

byn

-0.68

cad

-0.65

 bast

-0.63

acan

-0.63

POSITIVE LOGITS

 outwe

1.27

 negligible

1.21

 outweigh

1.16

 immense

1.13

 undeniable

1.09

 manifold

1.07

 limitless

1.02

 minimized

0.99

 minimal

0.98

 diminished

0.98

Activations Density 0.290%

adjectives describing the intensity or significance of potential consequences or impacts

phrases indicating the impact or consequences of actions or events

No Comments

No Known Activations