INDEX

Explanations

topics or keywords related to different subject areas or fields

oai_token-act-pair · gpt-3.5-turbo

empty or separator tokens indicating structure in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

otos

-0.94

atten

-0.73

atur

-0.73

 redemption

-0.72

yrus

-0.71

ript

-0.71

sis

-0.69

sole

-0.68

xes

-0.68

 destro

-0.68

POSITIVE LOGITS

Topics

1.18

afety

0.77

matter

0.76

 Flavoring

0.74

 Include

0.71

 EVENT

0.70

encies

0.67

Questions

0.66

peed

0.64

stuff

0.64

Activations Density 0.013%

topics or keywords related to different subject areas or fields

empty or separator tokens indicating structure in the text

No Comments

No Known Activations