INDEX

Explanations

mentions to check out something or take action related to a specific topic

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hots

-0.71

SAY

-0.71

 rendition

-0.66

ulton

-0.64

Ã±a

-0.64

ãĥĨãĤ£

-0.63

è£ħ

-0.63

ufact

-0.62

Ultimate

-0.61

Sin

-0.60

POSITIVE LOGITS

boxes

1.07

mate

1.01

lists

0.96

strap

0.91

box

0.89

enhagen

0.87

list

0.87

points

0.86

ups

0.84

etts

0.84

Activations Density 0.384%

mentions to check out something or take action related to a specific topic

No Comments

No Known Activations