INDEX

Explanations

numbers with percentages or statistical values

oai_token-act-pair · gpt-3.5-turbo

numerical data related to age and percentages

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

 Rica

-0.81

rencies

-0.81

terday

-0.69

awaru

-0.66

 Takeru

-0.66

sels

-0.65

 embassies

-0.64

 Sammy

-0.64

 fame

-0.64

 Rivals

-0.63

POSITIVE LOGITS

%-

1.11

acious

0.79

th

0.77

%"

0.76

0.75

teenth

0.75

percent

0.73

 dimensional

0.72

quel

0.72

Activations Density 0.103%

numbers with percentages or statistical values

numerical data related to age and percentages

No Comments

No Known Activations