INDEX

Explanations

mentions of specific events or entities indicated by the term "SA" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

references to specific licensing and attribution terms related to creative works

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

tons

-0.85

naire

-0.81

lace

-0.79

naires

-0.77

hower

-0.77

ships

-0.76

ysis

-0.74

starter

-0.69

sticks

-0.68

 MacArthur

-0.68

POSITIVE LOGITS

VE

1.36

ULT

1.07

ven

1.04

FE

1.02

ccess

0.97

pling

0.96

BILITY

0.95

BILITIES

0.95

plings

0.94

IDS

0.93

Activations Density 0.021%

mentions of specific events or entities indicated by the term "SA" followed by a numerical value

references to specific licensing and attribution terms related to creative works

No Comments

No Known Activations