INDEX

Explanations

phrases related to policies, systems, and regulations

oai_token-act-pair · gpt-3.5-turbo

statements regarding specific outcomes or impacts related to systems or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 mund

-0.77

 Cabrera

-0.65

uca

-0.64

rys

-0.64

emark

-0.62

lahoma

-0.62

iatus

-0.60

emen

-0.60

 Wander

-0.59

osaurus

-0.59

POSITIVE LOGITS

âĵĺ

0.98

Conclusion

0.96

Requires

0.94

Installation

0.93

Various

0.92

CONCLUS

0.91

Includes

0.90

Allows

0.88

Detailed

0.87

Synopsis

0.86

Activations Density 0.343%

phrases related to policies, systems, and regulations

statements regarding specific outcomes or impacts related to systems or policies

No Comments

No Known Activations