INDEX

Explanations

references to objects described as compact

oai_token-act-pair · gpt-3.5-turbo

references to compactness in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CVE

-0.91

Downloadha

-0.83

afia

-0.72

IGHTS

-0.69

opoulos

-0.68

hler

-0.67

govtrack

-0.66

cius

-0.65

hin

-0.64

ãĤ´ãĥ³

-0.64

POSITIVE LOGITS

 discs

0.86

arily

0.80

ness

0.80

nesses

0.80

 footprint

0.79

 fluorescent

0.79

 sized

0.76

icut

0.74

ened

0.73

 compact

0.73

Activations Density 0.025%

references to objects described as compact

references to compactness in various contexts

No Comments

No Known Activations