INDEX

Explanations

references to clocks or time-related words

oai_token-act-pair · gpt-3.5-turbo

occurrences and references to clocks or time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.87

BuyableInstoreAndOnline

-0.75

Sov

-0.74

 Nicarag

-0.74

rito

-0.70

ailability

-0.69

Ô

-0.69

Urban

-0.69

qua

-0.68

redients

-0.67

POSITIVE LOGITS

wise

1.06

work

1.03

clock

0.96

 Clock

0.92

 clock

0.90

tower

0.88

 clocks

0.87

 ticking

0.85

 ticks

0.83

maker

0.81

Activations Density 0.027%

references to clocks or time-related words

occurrences and references to clocks or time

No Comments

No Known Activations