INDEX

Explanations

words related to the name "Benjamin."

oai_token-act-pair · gpt-3.5-turbo

references to individuals and their affiliations

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

nesday

-0.75

peak

-0.73

 Hurricanes

-0.68

egg

-0.66

 Romantic

-0.62

 Mysteries

-0.60

TOP

-0.59

shut

-0.58

 millennium

-0.58

 Territories

-0.57

POSITIVE LOGITS

ussen

0.93

ophen

0.93

ergic

0.92

utations

0.88

å¥³

0.83

itial

0.83

strument

0.82

ifer

0.81

ors

0.81

uth

0.81

Activations Density 0.030%

words related to the name "Benjamin."

references to individuals and their affiliations

No Comments

No Known Activations