INDEX

Explanations

years or decades

oai_token-act-pair · gpt-3.5-turbo

mentions of decades or specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aukee

-0.68

 masc

-0.68

semble

-0.57

 fing

-0.57

dylib

-0.55

venge

-0.54

 Rivals

-0.53

avorite

-0.50

 probing

-0.50

 verbs

-0.50

POSITIVE LOGITS

1.29

ties

0.96

ixties

0.94

eties

0.89

ies

0.88

sie

0.84

enthal

0.83

sburg

0.78

-'

0.75

era

0.74

Activations Density 0.053%

years or decades

mentions of decades or specific years

No Comments

No Known Activations