INDEX

Explanations

references to specific environmental settings or conditions

oai_token-act-pair · gpt-3.5-turbo

terms associated with nature and environmental conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Flavoring

-0.85

sbm

-0.70

orsi

-0.67

zb

-0.65

apego

-0.64

illin

-0.64

henko

-0.63

fw

-0.63

utical

-0.62

compl

-0.61

POSITIVE LOGITS

 vicinity

0.96

 courtyard

0.86

 attic

0.84

 guise

0.82

 enclosure

0.82

 midst

0.81

 closet

0.77

 Indies

0.77

 classroom

0.75

 hurry

0.75

Activations Density 0.393%

references to specific environmental settings or conditions

terms associated with nature and environmental conditions

No Comments

No Known Activations