INDEX

Explanations

references to ongoing or potential investigations

oai_token-act-pair · gpt-3.5-turbo

references to investigative processes or inquiries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iewicz

-0.72

 VIDEOS

-0.72

ipation

-0.70

=]

-0.69

itudes

-0.68

ãĥĳ

-0.68

ops

-0.67

aign

-0.66

estyles

-0.65

($)

-0.65

POSITIVE LOGITS

omething

0.68

 dating

0.68

 sperm

0.64

gex

0.64

uana

0.63

aston

0.62

ersen

0.61

 chromosome

0.61

ahime

0.60

 chromos

0.59

Activations Density 0.000%

references to ongoing or potential investigations

references to investigative processes or inquiries

No Comments

No Known Activations