INDEX

Explanations

mentions of the location "Utica" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the string "Ut" followed by various characters, likely related to locations or organizations

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

Magikarp

-0.69

pmwiki

-0.68

boards

-0.67

backer

-0.66

 Leilan

-0.65

yond

-0.65

interstitial

-0.64

NetMessage

-0.64

 sear

-0.63

åħī

-0.62

POSITIVE LOGITS

ilitarian

1.43

ility

1.09

rue

1.08

tering

1.06

ils

1.03

ted

1.02

ter

1.00

ilities

0.97

aware

0.95

ropolis

0.94

Activations Density 0.016%

mentions of the location "Utica" in various contexts

occurrences of the string "Ut" followed by various characters, likely related to locations or organizations

No Comments

No Known Activations