INDEX

Explanations

statements expressing certainty or lack of evidence in a given situation

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

ares

-0.70

strip

-0.59

eal

-0.57

BI

-0.57

icut

-0.57

 towed

-0.56

agos

-0.56

 cylinders

-0.56

achi

-0.55

 endeavors

-0.55

POSITIVE LOGITS

 plenty

1.06

 ample

0.95

 overlap

0.87

no

0.86

 precedent

0.84

 lots

0.82

 disagreement

0.81

 variability

0.80

 alot

0.79

 precedence

0.79

Activations Density 0.720%

statements expressing certainty or lack of evidence in a given situation

No Comments

No Known Activations