INDEX

Explanations

keywords related to technical terms or names

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the term "ep."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 referen

-0.84

 nomine

-0.82

Ô

-0.79

ModLoader

-0.77

////////////////

-0.73

////////////////////////////////

-0.71

ãĤ´ãĥ³

-0.71

================================================================

-0.68

é¾

-0.65

CLASSIFIED

-0.64

POSITIVE LOGITS

isodes

1.31

odcast

1.19

ublic

1.13

hemer

1.11

iphany

1.11

artment

1.08

stakes

1.05

edia

1.05

osit

1.04

alm

0.97

Activations Density 0.010%

keywords related to technical terms or names

repeated mentions of the term "ep."

No Known Activations