INDEX

Explanations

movie-related information such as movie titles, actors, studios, and release dates

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

 trope

-0.89

 recess

-0.83

 offence

-0.83

 rush

-0.83

 background

-0.80

 foreground

-0.79

 routine

-0.78

 chase

-0.77

 sort

-0.77

 brute

-0.77

POSITIVE LOGITS

 Ventures

1.18

Bio

1.17

Soft

1.16

 Labs

1.16

Shares

1.11

 Interactive

1.11

 Analytics

1.09

Media

1.08

 Strategies

1.06

Works

1.05

Activations Density 1.810%

movie-related information such as movie titles, actors, studios, and release dates

No Comments

No Known Activations