INDEX

Explanations

phrases expressing contrast or impossibility

oai_token-act-pair · gpt-3.5-turbo

negation and phrases indicating isolation or lack

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aim

-0.79

ELD

-0.78

aku

-0.74

iple

-0.73

file

-0.73

alien

-0.70

ilon

-0.70

mitter

-0.68

arten

-0.68

{"

-0.66

POSITIVE LOGITS

acular

0.85

 necessarily

0.76

lihood

0.76

 anything

0.76

 outright

0.74

 Marketable

0.67

 possibly

0.66

å§«

0.65

 surpass

0.64

any

0.64

Activations Density 0.015%

phrases expressing contrast or impossibility

negation and phrases indicating isolation or lack

No Comments

No Known Activations