INDEX

Explanations

words related to prestigious awards and achievements

oai_token-act-pair · gpt-3.5-turbo

mentions of awards and nominations in the context of films and performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ullivan

-0.75

itness

-0.73

uba

-0.70

 breathing

-0.67

 atmosp

-0.67

ickr

-0.64

ths

-0.63

walking

-0.63

folk

-0.62

 visibly

-0.62

POSITIVE LOGITS

 Award

1.21

 Awards

1.18

Winner

1.02

 Winners

0.96

 nominations

0.94

 awards

0.94

 award

0.91

Cand

0.91

 Prize

0.90

 Winning

0.90

Activations Density 0.015%

words related to prestigious awards and achievements

mentions of awards and nominations in the context of films and performances

No Comments

No Known Activations