INDEX

Explanations

names that include "van der"

oai_token-act-pair · gpt-3.5-turbo

names and surnames with "van" or "der" in them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

estate

-0.87

ax

-0.87

anguage

-0.85

isp

-0.83

ascript

-0.83

perm

-0.83

illion

-0.83

enum

-0.82

illions

-0.80

alys

-0.79

POSITIVE LOGITS

Wa

1.02

Hoy

1.00

Gob

0.98

 Camb

0.97

 Bard

0.97

Sar

0.97

 Mayo

0.97

Hes

0.95

Ara

0.95

Boh

0.90

Activations Density 0.063%

names that include "van der"

names and surnames with "van" or "der" in them

No Comments

No Known Activations