INDEX

Explanations

dates and time-related words

oai_token-act-pair · gpt-3.5-turbo

events or occurrences that indicate significant changes or developments

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

ularity

-0.73

arez

-0.67

asu

-0.67

BUT

-0.66

But

-0.66

but

-0.64

arine

-0.63

 Dialogue

-0.63

 Travels

-0.62

iasis

-0.61

POSITIVE LOGITS

 nonetheless

1.05

etheless

1.04

 doubts

0.84

 caution

0.84

 nevertheless

0.82

 doubted

0.76

 cautioned

0.75

 opted

0.72

 surpr

0.70

 inexper

0.67

Activations Density 0.567%

dates and time-related words

events or occurrences that indicate significant changes or developments

No Comments

No Known Activations