INDEX

Explanations

concepts related to testing, accuracy, reliability, usability, credibility, and integrity

oai_token-act-pair · gpt-3.5-turbo

terms related to accuracy and reliability in assessments or evaluations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

onal

-0.81

inis

-0.71

joining

-0.68

rez

-0.68

folk

-0.68

ulla

-0.66

kson

-0.66

zen

-0.66

raine

-0.65

acters

-0.64

POSITIVE LOGITS

 assurance

0.94

 Guarant

0.92

BILITY

0.89

tests

0.88

 ratings

0.86

worthiness

0.85

 tests

0.85

 guarantees

0.83

 testing

0.82

 issues

0.82

Activations Density 0.188%

concepts related to testing, accuracy, reliability, usability, credibility, and integrity

terms related to accuracy and reliability in assessments or evaluations

No Comments

No Known Activations