INDEX

Explanations

mentions of a specific person or entity's actions or opinions

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "part" in different contexts

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

pload

-0.72

berus

-0.69

rys

-0.67

 adolesc

-0.66

ricane

-0.66

eli

-0.65

 pods

-0.64

 Rapt

-0.63

 grandchildren

-0.62

esome

-0.62

POSITIVE LOGITS

oubt

0.78

DoS

0.69

meal

0.68

uary

0.66

atum

0.66

ioned

0.66

ieu

0.66

lessness

0.65

displayText

0.64

offs

0.63

Activations Density 0.014%

mentions of a specific person or entity's actions or opinions

references to the concept of "part" in different contexts

No Comments

No Known Activations