INDEX

Explanations

information related to awards and nominations received by actors

oai_token-act-pair · gpt-3.5-turbo

recognition and awards related to acting achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rams

-0.79

cms

-0.77

athered

-0.72

umo

-0.71

bley

-0.69

tiny

-0.68

forums

-0.66

 brist

-0.65

anton

-0.65

iliar

-0.64

POSITIVE LOGITS

 Awards

1.08

 Award

1.06

 Songs

1.05

 Album

1.00

 Emmy

0.97

 Artist

0.84

 Grammy

0.83

 Title

0.83

 Series

0.82

 honors

0.82

Activations Density 0.108%

information related to awards and nominations received by actors

recognition and awards related to acting achievements

No Comments

No Known Activations