INDEX

Explanations

foreign characters and words

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

anwhile

-0.67

 undermin

-0.63

 destro

-0.62

aturdays

-0.61

 agre

-0.60

 athlet

-0.60

 disadvant

-0.59

 occas

-0.59

 conclud

-0.57

luster

-0.56

POSITIVE LOGITS

 âĢº

0.74

Ð¸

0.71

Ì

0.71

É

0.69

 ãĥ

0.67

Ð½

0.67

âĢİ

0.66

Ð²

0.65

Ä

0.64

Ñģ

0.64

Activations Density 0.236%

foreign characters and words

special characters or symbols

No Comments

No Known Activations