INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "embedding" or "embeddedness."

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

 corners

-0.76

 dime

-0.72

©¶æ

-0.70

 capsules

-0.68

peg

-0.67

 scales

-0.66

 flats

-0.64

 precedence

-0.62

rug

-0.62

 reservation

-0.62

POSITIVE LOGITS

enment

0.91

Allah

0.83

furt

0.78

lish

0.77

fitting

0.74

rel

0.72

force

0.72

arrass

0.71

lyn

0.70

riot

0.70

Activations Density 0.126%

names of individuals or entities

words related to the concept of "embedding" or "embeddedness."

No Comments

No Known Activations