INDEX

Explanations

phrases related to physical locations

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "in there."

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

 Abyss

-0.74

 Doctors

-0.64

 incumbent

-0.63

 Dresden

-0.60

 Stras

-0.59

 Geneva

-0.59

 recipient

-0.57

 Greens

-0.57

ably

-0.56

"],"

-0.54

POSITIVE LOGITS

abouts

1.19

tics

0.88

tical

0.86

tic

0.78

reck

0.76

comings

0.76

with

0.73

 nodd

0.73

alse

0.70

ritic

0.69

Activations Density 0.045%

phrases related to physical locations

the repeated phrase "in there."

No Comments

No Known Activations