INDEX

Explanations

phrases indicating something is not as expected or negative in nature

oai_token-act-pair · gpt-3.5-turbo

phrases expressing negation or insignificance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PLA

-0.71

 caches

-0.65

 Roots

-0.65

 reper

-0.64

uctions

-0.62

rises

-0.59

 downs

-0.58

 floors

-0.57

 openings

-0.56

 emphasis

-0.56

POSITIVE LOGITS

ĸļ

0.99

BuyableInstoreAndOnline

0.76

renheit

0.74

 akin

0.73

lled

0.69

clud

0.69

ueller

0.67

 extraord

0.67

dimensional

0.66

parable

0.66

Activations Density 0.139%

phrases indicating something is not as expected or negative in nature

phrases expressing negation or insignificance

No Comments

No Known Activations