INDEX

Explanations

brand names and product names

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically commas

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

etheless

-0.52

ilater

-0.46

latest

-0.45

cause

-0.44

requisite

-0.43

sbm

-0.42

ertodd

-0.42

summary

-0.42

scient

-0.42

umbn

-0.41

POSITIVE LOGITS

1.63

,...

1.12

,[

1.01

0.94

0.89

,.

0.87

,,

0.86

.,

0.86

,—

0.86

!,

0.85

Activations Density 2.356%

brand names and product names

punctuation marks, specifically commas

No Known Activations