INDEX

Explanations

occurrences of the term "Nar" or similar sequences, possibly related to specific entities or topics

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Nar."

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

 Pixie

-0.92

 Democr

-0.87

éĹĺ

-0.78

 Canary

-0.78

IBLE

-0.70

xual

-0.70

 Wink

-0.69

 Lego

-0.69

 VIDEOS

-0.69

 Extrem

-0.67

POSITIVE LOGITS

ration

1.01

ayan

1.01

rils

0.97

opa

0.94

ril

0.91

aya

0.89

Nar

0.88

aband

0.86

uno

0.86

 Lumpur

0.85

Activations Density 0.013%

occurrences of the term "Nar" or similar sequences, possibly related to specific entities or topics

mentions of the word "Nar."

No Comments

No Known Activations