INDEX

Explanations

numeric values related to prices, quantities, measurements, rankings, and percentages

oai_token-act-pair · gpt-3.5-turbo

numerical data and percentages related to financial or statistical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 quir

-0.68

 neighb

-0.65

 somew

-0.63

 exha

-0.61

chwitz

-0.60

uca

-0.59

 rall

-0.58

 conserv

-0.58

 Palest

-0.58

 cooperating

-0.55

POSITIVE LOGITS

 Female

0.71

 Retrieved

0.69

 Difference

0.65

[+

0.65

 Male

0.64

Loading

0.64

[-

0.64

Female

0.62

 Amount

0.62

 Notes

0.60

Activations Density 0.355%

numeric values related to prices, quantities, measurements, rankings, and percentages

numerical data and percentages related to financial or statistical contexts

No Comments

No Known Activations