INDEX

Explanations

dates mentioned with years

oai_token-act-pair · gpt-3.5-turbo

specific years in the context of events or dates

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

amins

-0.65

 verbs

-0.61

 enchantment

-0.60

onite

-0.60

Reloaded

-0.59

 endless

-0.58

 Wonders

-0.57

 bona

-0.57

und

-0.57

fam

-0.57

POSITIVE LOGITS

burgh

0.71

 partName

0.66

ramid

0.66

RHP

0.65

âĸĪ

0.65

 Became

0.65

isSpecialOrderable

0.64

âĢ²

0.64

displayText

0.62

mr

0.61

Activations Density 0.074%

dates mentioned with years

specific years in the context of events or dates

No Comments

No Known Activations