INDEX

Explanations

locations or entities related to the word "Lat"

oai_token-act-pair · gpt-3.5-turbo

references to "Lat" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

OHN

-0.78

éĹĺ

-0.78

MODE

-0.74

æĸ¹

-0.74

ãģ®éŃĶ

-0.72

EMENT

-0.71

vironment

-0.70

NCT

-0.69

 Annotations

-0.68

ushima

-0.68

POSITIVE LOGITS

itude

1.14

itud

1.09

itudinal

1.08

itudes

0.97

imes

0.96

ency

0.95

akia

0.93

robe

0.90

ories

0.79

ius

0.76

Activations Density 0.026%

locations or entities related to the word "Lat"

references to "Lat" and variations of it

No Comments

No Known Activations