INDEX

Explanations

words or phrases related to the anatomical structure 'rib'

oai_token-act-pair · gpt-3.5-turbo

terms related to rib injuries or medical conditions involving ribs

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

 Sunny

-0.85

 GOODMAN

-0.77

SOS

-0.74

 Ceres

-0.69

eanor

-0.68

 Claus

-0.68

ainment

-0.67

 Esper

-0.64

 Valhalla

-0.64

ADRA

-0.63

POSITIVE LOGITS

bons

1.39

bed

1.00

bent

0.99

Rib

0.94

bones

0.90

aldi

0.90

bing

0.90

rib

0.87

bon

0.87

acies

0.87

Activations Density 0.010%

words or phrases related to the anatomical structure 'rib'

terms related to rib injuries or medical conditions involving ribs

No Comments

No Known Activations