INDEX

Explanations

descriptions related to characteristics or qualities of different objects or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases and words that convey emotional intensity or descriptions of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iatus

-0.67

exempt

-0.64

ABE

-0.64

erous

-0.63

 Provision

-0.62

enary

-0.60

ãĥ¯ãĥ³

-0.60

 Archive

-0.59

idential

-0.58

copy

-0.58

POSITIVE LOGITS

 playful

0.71

 reminiscent

0.70

 mesmer

0.69

 gorge

0.68

 exhilar

0.67

 pleasing

0.67

 intox

0.65

 shades

0.65

 refreshing

0.64

 capt

0.63

Activations Density 0.903%

descriptions related to characteristics or qualities of different objects or concepts

phrases and words that convey emotional intensity or descriptions of experiences

No Comments

No Known Activations