INDEX

Explanations

phrases referring to actions or characteristics done individually

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to autonomy and independence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obar

-0.81

recated

-0.81

mers

-0.79

anwhile

-0.75

olic

-0.74

gerald

-0.71

osi

-0.68

————————

-0.68

thouse

-0.67

amac

-0.67

POSITIVE LOGITS

 accord

0.92

Cloud

0.84

 backyard

0.76

 footing

0.73

 merits

0.70

 detriment

0.70

 initiative

0.69

 hands

0.68

 turf

0.65

 discretion

0.64

Activations Density 0.034%

phrases referring to actions or characteristics done individually

phrases and terms related to autonomy and independence

No Comments

No Known Activations