INDEX

Explanations

mentions of publications or works being published

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llan

-0.82

mer

-0.72

xa

-0.72

nea

-0.71

ugh

-0.71

 awoken

-0.70

phant

-0.69

bones

-0.69

enhagen

-0.68

aura

-0.68

POSITIVE LOGITS

lishing

1.24

lisher

1.05

 excerpts

1.03

lishes

0.96

 publication

0.85

 publishing

0.81

 articles

0.78

 journals

0.78

 Journals

0.77

 journal

0.76

Activations Density 0.051%

mentions of publications or works being published

No Comments

No Known Activations