INDEX

Explanations

prepositions indicating a specific point in time

oai_token-act-pair · gpt-3.5-turbo

the phrase "prior to" and its variations in 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

among

-0.93

backed

-0.68

Rated

-0.67

Girls

-0.66

ById

-0.66

RAM

-0.65

erto

-0.63

OVER

-0.63

LED

-0.62

 ILCS

-0.62

POSITIVE LOGITS

 embark

0.96

 completion

0.82

 fruition

0.78

imester

0.78

 sunset

0.77

uberty

0.76

 publication

0.76

 launch

0.76

 noon

0.74

 commencement

0.73

Activations Density 0.040%

prepositions indicating a specific point in time

the phrase "prior to" and its variations in context

No Comments

No Known Activations