INDEX

Explanations

uncertain, investigative, and explanatory contexts in a news or report writing setting

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

tic

-0.74

Less

-0.73

 beware

-0.69

itton

-0.67

thal

-0.65

ĸļ

-0.64

Zone

-0.64

yton

-0.64

chall

-0.63

ngth

-0.63

POSITIVE LOGITS

 specifics

1.40

nor

1.17

 definitively

1.00

 anymore

0.95

 conclusive

0.92

 specific

0.91

 definitive

0.91

 formally

0.90

 exact

0.88

 officially

0.86

Activations Density 1.397%

uncertain, investigative, and explanatory contexts in a news or report writing setting

No Comments

No Known Activations