INDEX

Explanations

unique terms or names mentioned in a specific context, potentially related to details or distinctions

oai_token-act-pair · gpt-3.5-turbo

words related to various sports and competition achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 earthqu

-0.77

 referen

-0.71

 eleph

-0.71

Orderable

-0.70

oreAnd

-0.67

 pione

-0.65

ThumbnailImage

-0.64

 subur

-0.60

 immigrants

-0.60

 plead

-0.60

POSITIVE LOGITS

kaya

0.78

opian

0.74

iman

0.72

antes

0.71

rette

0.69

abo

0.68

aceous

0.68

oso

0.67

nexus

0.67

agen

0.66

Activations Density 0.086%

unique terms or names mentioned in a specific context, potentially related to details or distinctions

words related to various sports and competition achievements

No Comments

No Known Activations