INDEX

Explanations

names or terms related to specific individuals or characters

oai_token-act-pair · gpt-3.5-turbo

repeated references to specific names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

oun

-0.83

inventoryQuantity

-0.73

 Flavoring

-0.73

edIn

-0.67

itely

-0.66

acles

-0.66

hips

-0.66

edin

-0.64

anke

-0.64

nesday

-0.63

POSITIVE LOGITS

trap

0.84

Dum

0.74

BOOK

0.71

Ñĭ

0.71

urat

0.70

 Chap

0.69

Book

0.69

ments

0.69

Topic

0.67

aign

0.67

Activations Density 0.022%

names or terms related to specific individuals or characters

repeated references to specific names or titles

No Comments

No Known Activations