INDEX

Explanations

proper nouns related to hotels or locations

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Ritz" associated with various contexts or mentions

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

 livest

-0.76

 Pradesh

-0.68

 unden

-0.67

Interstitial

-0.65

 arming

-0.65

ACTED

-0.65

 notor

-0.65

auga

-0.64

cknow

-0.63

 occas

-0.63

POSITIVE LOGITS

gerald

1.64

patrick

1.21

sch

1.15

itz

1.08

heimer

1.05

enger

1.00

aic

0.94

enegger

0.93

roth

0.93

geist

0.89

Activations Density 0.016%

proper nouns related to hotels or locations

instances of the name "Ritz" associated with various contexts or mentions

No Comments

No Known Activations