INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the name "Gwen" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ĺħ

-0.72

 coordinate

-0.69

ocre

-0.68

Pwr

-0.68

 offense

-0.66

 offence

-0.65

 practicable

-0.65

 plural

-0.65

osate

-0.65

rador

-0.64

POSITIVE LOGITS

wen

1.49

burn

1.03

borough

1.02

 Kenobi

0.89

boro

0.88

jen

0.87

zona

0.86

mere

0.86

pool

0.86

igan

0.86

Activations Density 0.004%

proper nouns

the occurrences of the name "Gwen" and its variations in the text

No Comments

No Known Activations