INDEX

Explanations

adjectives related to reliability

oai_token-act-pair · gpt-3.5-turbo

references to the concept of reliability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

owitz

-0.86

horn

-0.83

ften

-0.80

agall

-0.78

ifling

-0.77

amaru

-0.75

mare

-0.74

ophy

-0.74

eanor

-0.73

onia

-0.72

POSITIVE LOGITS

 reliability

1.12

 reliable

1.12

iability

0.95

 unreliable

0.95

 estim

0.90

iable

0.88

 trustworthy

0.87

 sust

0.85

 narrator

0.84

 intervals

0.81

Activations Density 0.020%

adjectives related to reliability

references to the concept of reliability

No Comments

No Known Activations