INDEX

Explanations

phrases related to completion or accomplishment

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol

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

•GPT2 L5 Resid: RRLLRLLRLLRRRRLLRRRRRRRRR

No Comments

Negative Logits

 Samar

-0.58

 scattering

-0.58

anwhile

-0.55

 scatter

-0.55

 decomp

-0.54

 rotating

-0.53

 guiActiveUnfocused

-0.52

 unmarked

-0.50

itably

-0.49

 scramble

-0.49

POSITIVE LOGITS

¹

0.81

¬

0.78

£

0.75

catentry

0.74

º

0.73

Â¯

0.71

į

0.69

Â§

0.67

acca

0.67

ı

0.67

Activations Density 0.541%

phrases related to completion or accomplishment

occurrences of a specific character or symbol

No Comments

No Known Activations