INDEX

Explanations

phrases containing the character "ö"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character "ö"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Crusader

-0.71

tons

-0.68

 Watson

-0.68

 Bengal

-0.67

orers

-0.63

 Hercules

-0.61

 Crus

-0.60

 Virgin

-0.60

 Akron

-0.60

 Blacks

-0.60

POSITIVE LOGITS

andom

1.04

Ã°

1.01

Ã¶

0.98

Ã¶r

0.93

sson

0.84

ping

0.81

Ã¶n

0.81

Ã¡n

0.79

sten

0.78

onto

0.78

Activations Density 0.006%

phrases containing the character "ö"

occurrences of the character "ö"

No Comments

No Known Activations