INDEX

Explanations

words related to episodic memory and experiences

oai_token-act-pair · gpt-3.5-turbo

references to episodes or segments from a series or program

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

FUL

-0.93

hips

-0.79

LESS

-0.77

folk

-0.74

Pru

-0.73

holding

-0.67

 nomine

-0.66

ÙĲ

-0.66

''''

-0.65

veyard

-0.65

POSITIVE LOGITS

iphany

1.41

istle

1.25

iscopal

1.23

hemer

1.21

isodes

1.17

onymous

1.09

idem

1.04

iph

0.98

isc

0.96

otrop

0.96

Activations Density 0.018%

words related to episodic memory and experiences

references to episodes or segments from a series or program

No Comments

No Known Activations