INDEX

Explanations

terms related to compactness

oai_token-act-pair · gpt-3.5-turbo

terms related to compactness or small size

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

CVE

-0.92

Downloadha

-0.83

opoulos

-0.79

hler

-0.73

govtrack

-0.69

FORE

-0.65

afa

-0.65

hod

-0.65

afia

-0.64

aina

-0.63

POSITIVE LOGITS

 discs

0.87

nesses

0.84

 fluorescent

0.78

ness

0.77

ened

0.76

 footprint

0.74

 sized

0.70

 disks

0.70

 Compact

0.70

 compact

0.70

Activations Density 0.030%

terms related to compactness

terms related to compactness or small size

No Comments

No Known Activations