INDEX

Explanations

locations and specific details mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

specific phrases indicating locations or quantities related to events and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

apult

-0.63

andise

-0.60

atican

-0.60

 Mages

-0.59

arta

-0.59

puter

-0.58

ascript

-0.57

 Creatures

-0.57

 THESE

-0.57

 Rampage

-0.56

POSITIVE LOGITS

roads

0.77

hots

0.73

pload

0.70

geries

0.69

cro

0.67

ingly

0.65

lim

0.65

hurst

0.64

iw

0.64

etically

0.64

Activations Density 0.410%

locations and specific details mentioned in the text

specific phrases indicating locations or quantities related to events and entities

No Comments

No Known Activations