INDEX

Explanations

words related to the ancient civilization of Sumer

oai_token-act-pair · gpt-3.5-turbo

references to specific sums or totals

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

enhagen

-0.70

©¶æ¥µ

-0.67

 levers

-0.61

jriwal

-0.60

MRI

-0.60

 surg

-0.60

hent

-0.59

atcher

-0.59

 whiff

-0.58

 holster

-0.56

POSITIVE LOGITS

ua

0.75

zees

0.72

atural

0.66

ript

0.64

oga

0.62

dam

0.61

ophon

0.60

hua

0.58

ederal

0.57

ST

0.57

Activations Density 0.142%

words related to the ancient civilization of Sumer

references to specific sums or totals

No Comments

No Known Activations