INDEX

Explanations

verbs indicating action or application of something to a specific object or context

oai_token-act-pair · gpt-3.5-turbo

action verbs related to processes or actions that are being taken or executed

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

ajo

-0.77

ylum

-0.66

 Vaughan

-0.65

Doctors

-0.62

Irish

-0.62

iland

-0.61

anmar

-0.61

ierre

-0.61

eah

-0.60

paio

-0.60

POSITIVE LOGITS

 properly

0.95

 correctly

0.78

 individually

0.77

 incorrectly

0.70

 exceeds

0.68

 perpend

0.67

});

0.65

 scientifically

0.64

 improperly

0.64

 numer

0.61

Activations Density 0.087%

verbs indicating action or application of something to a specific object or context

action verbs related to processes or actions that are being taken or executed

No Comments

No Known Activations