INDEX

Explanations

words related to the reliability and usability of products or theories

oai_token-act-pair · gpt-3.5-turbo

terms related to assessment and evaluation of reliability and usability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

inis

-0.80

onal

-0.78

raine

-0.72

 Wick

-0.67

eric

-0.67

goers

-0.62

Pic

-0.62

ulla

-0.62

Lens

-0.61

joining

-0.61

POSITIVE LOGITS

worthiness

1.00

 mismatch

0.93

 ratings

0.93

ability

0.90

iencies

0.85

BILITY

0.83

 testing

0.83

abilities

0.82

 assurance

0.81

 rating

0.80

Activations Density 0.191%

words related to the reliability and usability of products or theories

terms related to assessment and evaluation of reliability and usability

No Comments

No Known Activations