INDEX

Explanations

information related to personal experiences and stories

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

ilty

-0.73

 resemblance

-0.71

oplan

-0.70

ieth

-0.68

orage

-0.68

represent

-0.64

Arab

-0.64

anty

-0.64

Lat

-0.63

YS

-0.62

POSITIVE LOGITS

 resorted

1.16

 devised

0.95

 decided

0.94

 reluctantly

0.91

 resort

0.91

 recourse

0.91

 hurried

0.90

 resorts

0.89

 opted

0.88

 hastily

0.86

Activations Density 2.474%

information related to personal experiences and stories

No Comments

No Known Activations