INDEX

Explanations

numerical values and measurements, as well as alphanumeric codes and identifiers

oai_token-act-pair · gpt-3.5-turbo

numerical values and references to programming elements or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 eleph

-0.92

Þ

-0.89

ß

-0.80

 pione

-0.78

 tremend

-0.78

 exting

-0.77

 occas

-0.77

ò

-0.76

aditional

-0.76

oun

-0.76

POSITIVE LOGITS

eret

0.48

Merit

0.48

wcsstore

0.47

athan

0.45

't

0.44

bryce

0.43

gex

0.43

Course

0.43

thereum

0.43

forge

0.43

Activations Density 0.938%

numerical values and measurements, as well as alphanumeric codes and identifiers

numerical values and references to programming elements or components

No Comments

No Known Activations