INDEX

Explanations

named organizations or entities with a possessive form indicating ownership or association

oai_token-act-pair · gpt-3.5-turbo

possessive forms denoting ownership or association

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

ETS

-0.77

etry

-0.77

ivities

-0.76

PLA

-0.76

views

-0.75

izons

-0.75

linux

-0.72

ulations

-0.72

hm

-0.71

events

-0.71

POSITIVE LOGITS

 keeper

1.13

 centerpiece

1.07

 youngest

1.04

 ambassador

1.02

 mascot

1.02

 successor

1.01

 flagship

1.01

 oldest

1.00

 biggest

0.99

 favorite

0.97

Activations Density 0.130%

named organizations or entities with a possessive form indicating ownership or association

possessive forms denoting ownership or association

No Comments

No Known Activations