INDEX

Explanations

descriptors related to reliability and dependability

oai_token-act-pair · gpt-3.5-turbo

references to reliability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ovember

-0.84

owitz

-0.79

aeper

-0.78

kay

-0.78

eanor

-0.74

ften

-0.73

ophon

-0.72

ema

-0.71

obia

-0.71

ãħĭ

-0.71

POSITIVE LOGITS

 reliable

1.05

 narrator

0.93

iability

0.90

 reliability

0.85

 source

0.84

 trustworthy

0.84

 unreliable

0.84

 assurance

0.78

 isot

0.77

 indicator

0.75

Activations Density 0.064%

descriptors related to reliability and dependability

references to reliability in various contexts

No Comments

No Known Activations