INDEX

Explanations

numeric data related to arrays

oai_token-act-pair · gpt-3.5-turbo

references to arrays in various contexts

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

SF

-0.68

é¾įå¥ĳå£«

-0.66

mins

-0.63

trade

-0.62

ABE

-0.61

 McKenna

-0.61

 Cthulhu

-0.61

dom

-0.60

Gordon

-0.60

 Upton

-0.59

POSITIVE LOGITS

 subscript

0.83

 array

0.82

mble

0.79

icter

0.70

arium

0.70

 holdings

0.69

Buffer

0.69

 encomp

0.68

imony

0.68

 comprised

0.67

Activations Density 0.016%

numeric data related to arrays

references to arrays in various contexts

No Comments

No Known Activations