INDEX

Explanations

formal indications or signals

oai_token-act-pair · gpt-3.5-turbo

phrases that denote signaling or indication of conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ctors

-0.83

fare

-0.76

@#&

-0.76

ernels

-0.68

jan

-0.68

 helicop

-0.68

zan

-0.68

sites

-0.67

assic

-0.67

Sah

-0.66

POSITIVE LOGITS

 indications

0.86

ively

0.85

 displeasure

0.82

 willingness

0.79

 signs

0.78

ered

0.77

manship

0.77

ially

0.76

 preference

0.74

iveness

0.71

Activations Density 0.041%

formal indications or signals

phrases that denote signaling or indication of conditions

No Comments

No Known Activations