INDEX

Explanations

proper nouns related to the name "Hamilton."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Hamilton"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lihood

-0.83

xp

-0.71

eker

-0.69

gger

-0.65

erred

-0.65

llan

-0.64

hl

-0.63

herer

-0.63

baugh

-0.60

ramid

-0.60

POSITIVE LOGITS

pton

0.93

 Strait

0.89

ipeg

0.85

ians

0.83

iere

0.82

enburg

0.81

 Heights

0.78

Hamilton

0.76

 Tiger

0.74

igans

0.74

Activations Density 0.051%

proper nouns related to the name "Hamilton."

mentions of the term "Hamilton"

No Comments

No Known Activations