INDEX

Explanations

prepositional phrases denoting location or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and related expressions indicating location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

berman

-0.69

 Kinnikuman

-0.65

 Issa

-0.64

orius

-0.63

bara

-0.62

tab

-0.62

ãħĭãħĭ

-0.60

agues

-0.60

etc

-0.60

 ordinances

-0.58

POSITIVE LOGITS

cluding

0.73

ordable

0.72

oping

0.71

iliated

0.67

ãĥĨãĤ£

0.65

ãĥ©ãĥ³

0.65

illery

0.64

vol

0.64

otton

0.63

TAIN

0.63

Activations Density 0.391%

prepositional phrases denoting location or position

occurrences of the word "in" and related expressions indicating location or context

No Comments

No Known Activations