INDEX

Explanations

technical terms related to tasks, technical environments, and issues faced by robots

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

amaz

-0.77

guyen

-0.73

atorium

-0.71

raid

-0.70

rique

-0.65

DOS

-0.65

psc

-0.64

own

-0.63

onel

-0.63

ACTED

-0.61

POSITIVE LOGITS

 imaginable

1.16

 pertaining

1.14

 relating

1.14

 including

1.11

 ranging

1.07

 affecting

1.07

 besides

0.98

hooting

0.97

uits

0.97

paces

0.97

Activations Density 1.976%

technical terms related to tasks, technical environments, and issues faced by robots

No Comments

No Known Activations