INDEX

Explanations

the color "blue"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "blue."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ROR

-0.89

IFA

-0.77

ETF

-0.76

Allow

-0.75

ORTS

-0.75

Dur

-0.72

Demand

-0.72

Ö¼

-0.72

 Inspect

-0.72

AMI

-0.71

POSITIVE LOGITS

prints

1.26

berry

1.19

 violet

1.15

grass

1.09

 ribbon

1.01

 colored

0.97

 coloured

0.97

dye

0.96

beard

0.93

 blue

0.93

Activations Density 0.013%

the color "blue"

occurrences of the word "blue."

No Comments

No Known Activations