INDEX

Explanations

phrases related to required actions or resources

oai_token-act-pair · gpt-3.5-turbo

words related to requirements and necessities

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

atever

-0.77

ierre

-0.73

ttle

-0.71

actionDate

-0.69

udeau

-0.69

adier

-0.68

otonin

-0.66

pan

-0.64

ookie

-0.64

ensional

-0.63

POSITIVE LOGITS

 herein

0.89

 therein

0.89

 thereto

0.75

 incurred

0.75

 contained

0.72

 encountered

0.69

 spawned

0.67

 determines

0.67

 emanating

0.66

 afforded

0.65

Activations Density 0.242%

phrases related to required actions or resources

words related to requirements and necessities

No Comments

No Known Activations