INDEX

Explanations

capitalized words

oai_token-act-pair · gpt-3.5-turbo

subject pronouns or possessive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 noses

-0.65

 recip

-0.65

 vain

-0.65

 nose

-0.65

voc

-0.64

 nodd

-0.63

 cutter

-0.63

 judgment

-0.63

 submar

-0.63

 grav

-0.62

POSITIVE LOGITS

edes

0.76

Guard

0.76

itech

0.76

 Them

0.76

oran

0.72

Torrent

0.72

zac

0.72

Week

0.72

ussie

0.72

Mind

0.72

Activations Density 0.221%

capitalized words

subject pronouns or possessive pronouns

No Comments

No Known Activations